Skip to content
Launchpad Library logo

Projects hub

Every open-source project here, with the steps to run it

121 projects in one place: the 50 written up by hand on Free AI Projects (licenses read from their own license files on 22 September 2026), plus the open-source entries from the tools library. Each one shows what it does, the license it carries, and a run-it guide. Where the person who built it has a Who’s Who profile, they are named on the card.

Being straight about the guides: they are the same honest sequence for every project of a shape, and the last step always sends you to the project’s own README or model card. The exact install command belongs to the project and changes — inventing one here would only go stale. Library entries show the license their own page names; the ones marked as read were checked against the license file.

Wanted a tool rather than something to run?

The Tools page is the wider list: every tool in the library, free or paid, grouped by the job it helps with, with what each one costs. This page is the narrower one — only projects whose code is open, each with its license and the steps to run it.

121 matching projects.

Ollama

MIT

Ollama

Downloads and runs open models with one command, and serves them to other programs on your machine.

What you need to run it: A normal laptop will run a small model. Around 8GB of memory for a 7–8 billion parameter model; more memory means bigger models, a graphics card means faster ones.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/ollama/ollama.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageRun a model on your own computer

llama.cpp

MIT

ggml / Georgi Gerganov

The engine underneath most local AI apps. Runs models in a compressed format on ordinary hardware, including old machines.

What you need to run it: Comfortable with a terminal. You compile it, or download a release build, then point it at a model file.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/ggml-org/llama.cpp.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageRun a model on your own computer

LocalAI

MIT

Ettore Di Giacinto

A drop-in replacement for the OpenAI API that runs on your own hardware, covering text, images, speech and vision.

What you need to run it: Docker, or a single binary. No graphics card required, though one helps.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/mudler/LocalAI.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageRun a model on your own computer

Menlo Research

A desktop app that looks like a chat app and runs models entirely offline on your machine.

What you need to run it: Download and install, like any other app. No account, no terminal.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/janhq/jan.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageRun a model on your own computer

GPT4All

MIT

Nomic AI

Desktop app for chatting with local models, including over your own folder of documents.

What you need to run it: An installer for Windows, Mac or Linux. Works without a graphics card.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/nomic-ai/gpt4all.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageRun a model on your own computer

Open WebUI Inc.

A polished browser interface over Ollama or any OpenAI-compatible API, with users, chat history and document search.

What you need to run it: Docker or Python, and a model source such as Ollama running alongside it.

Read the license first: Not a standard open-source license. It is BSD-3 with an added clause about keeping the Open WebUI branding unless you have 50 or fewer users or a separate agreement. Fine for personal and small-team use; read it before you rebrand it for a client.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/open-webui/open-webui.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageRun a model on your own computer

AnythingLLM

MIT

Mintplex Labs

A local-first workspace that answers questions over your own documents, with agents and multiple users.

What you need to run it: Desktop app or Docker. Bring your own local or hosted model.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/Mintplex-Labs/anything-llm.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageRun a model on your own computer

LibreChat

MIT

Danny Avila

A self-hosted chat interface that puts local and hosted models side by side in one place.

What you need to run it: Docker and a little configuration. Best if you already host things.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/danny-avila/LibreChat.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageRun a model on your own computer

Text generation web UI

AGPL-3.0

oobabooga

A desktop app and web interface for local models, with tool calling and an OpenAI-compatible API.

What you need to run it: A one-click installer, then a model file. A graphics card makes it far more pleasant.

Read the license first: Strong copyleft. Using it yourself is unrestricted, but if you modify it and let other people use it over a network, you have to publish your changes.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/oobabooga/text-generation-webui.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageRun a model on your own computer

gpt-oss-20b

Apache-2.0

OpenAI

OpenAI's open-weight model, released for anyone to download and run — including commercially.

What you need to run it: Roughly 16GB of memory in its compressed form. Runs in Ollama or llama.cpp without special setup.

Who’s Who connected to it

  • Sam AltmanRuns OpenAI, which released these open weights. The training work is the lab's, not his own code.
How to run it yourself

These are model weights: a file you download, plus a program from the first section of the Free AI Projects page to load it.

  1. Install a runner first — Ollama is the shortest route, llama.cpp if you want the engine itself.
  2. Open the model card on this card's link and read the license and the size before downloading anything.
  3. Pick the size that fits your machine: a smaller, more compressed file if you have 8GB of memory, a larger one if you have a graphics card.
  4. Download it the way the model card says, then load it in your runner and ask it something you already know the answer to.
  5. Check the answer quality yourself on your own work — benchmark numbers on a model card are the maker's own.
  6. Read the license before commercial use: some open-weight models restrict it.
Model cardOpen model weights you can download

Alibaba Cloud (Qwen team)

A family of models from tiny to very large, strong on reasoning and on languages other than English.

What you need to run it: The 8-billion version runs on a laptop with about 8GB free. Larger sizes need a GPU.

How to run it yourself

These are model weights: a file you download, plus a program from the first section of the Free AI Projects page to load it.

  1. Install a runner first — Ollama is the shortest route, llama.cpp if you want the engine itself.
  2. Open the model card on this card's link and read the license and the size before downloading anything.
  3. Pick the size that fits your machine: a smaller, more compressed file if you have 8GB of memory, a larger one if you have a graphics card.
  4. Download it the way the model card says, then load it in your runner and ask it something you already know the answer to.
  5. Check the answer quality yourself on your own work — benchmark numbers on a model card are the maker's own.
  6. Read the license before commercial use: some open-weight models restrict it.
Model cardOpen model weights you can download

Mistral 7B Instruct

Apache-2.0

Mistral AI

A small, fast, open model that still holds up for summarizing, drafting and classification.

What you need to run it: About 5GB compressed. One of the easiest first models to run.

Who’s Who connected to it

  • Arthur MenschCo-founded Mistral AI and runs it; the company trained and released these weights.
How to run it yourself

These are model weights: a file you download, plus a program from the first section of the Free AI Projects page to load it.

  1. Install a runner first — Ollama is the shortest route, llama.cpp if you want the engine itself.
  2. Open the model card on this card's link and read the license and the size before downloading anything.
  3. Pick the size that fits your machine: a smaller, more compressed file if you have 8GB of memory, a larger one if you have a graphics card.
  4. Download it the way the model card says, then load it in your runner and ask it something you already know the answer to.
  5. Check the answer quality yourself on your own work — benchmark numbers on a model card are the maker's own.
  6. Read the license before commercial use: some open-weight models restrict it.
Model cardOpen model weights you can download

Phi-4-mini-instruct

MIT

Microsoft

A small model trained on carefully filtered data, aimed at reasoning well for its size.

What you need to run it: Runs on a laptop. No GPU needed for the compressed version.

Who’s Who connected to it

  • Satya Nadellatheir company’s repository, not their own codeRuns Microsoft, whose research team trained and released the Phi models.
How to run it yourself

These are model weights: a file you download, plus a program from the first section of the Free AI Projects page to load it.

  1. Install a runner first — Ollama is the shortest route, llama.cpp if you want the engine itself.
  2. Open the model card on this card's link and read the license and the size before downloading anything.
  3. Pick the size that fits your machine: a smaller, more compressed file if you have 8GB of memory, a larger one if you have a graphics card.
  4. Download it the way the model card says, then load it in your runner and ask it something you already know the answer to.
  5. Check the answer quality yourself on your own work — benchmark numbers on a model card are the maker's own.
  6. Read the license before commercial use: some open-weight models restrict it.
Model cardOpen model weights you can download

SmolLM3-3B

Apache-2.0

Hugging Face

A tiny model published with its training recipe, so you can see how it was made, not just use it.

What you need to run it: Runs on modest hardware, including some phones and single-board computers.

Who’s Who connected to it

  • Clément DelangueCo-founded Hugging Face and runs it; this is one of the company's own trained models.
How to run it yourself

These are model weights: a file you download, plus a program from the first section of the Free AI Projects page to load it.

  1. Install a runner first — Ollama is the shortest route, llama.cpp if you want the engine itself.
  2. Open the model card on this card's link and read the license and the size before downloading anything.
  3. Pick the size that fits your machine: a smaller, more compressed file if you have 8GB of memory, a larger one if you have a graphics card.
  4. Download it the way the model card says, then load it in your runner and ask it something you already know the answer to.
  5. Check the answer quality yourself on your own work — benchmark numbers on a model card are the maker's own.
  6. Read the license before commercial use: some open-weight models restrict it.
Model cardOpen model weights you can download

Allen Institute for AI

A fully open model: weights, training data, code and checkpoints all published. The one to use if you need to know what went in.

What you need to run it: A GPU for the 7-billion version, or run a compressed build locally.

How to run it yourself

These are model weights: a file you download, plus a program from the first section of the Free AI Projects page to load it.

  1. Install a runner first — Ollama is the shortest route, llama.cpp if you want the engine itself.
  2. Open the model card on this card's link and read the license and the size before downloading anything.
  3. Pick the size that fits your machine: a smaller, more compressed file if you have 8GB of memory, a larger one if you have a graphics card.
  4. Download it the way the model card says, then load it in your runner and ask it something you already know the answer to.
  5. Check the answer quality yourself on your own work — benchmark numbers on a model card are the maker's own.
  6. Read the license before commercial use: some open-weight models restrict it.
Model cardOpen model weights you can download

Llama 3.3 70B Instruct

Llama 3.3 Community License

Meta

Meta's large open-weight model, widely used as the baseline for self-hosted work.

What you need to run it: Serious hardware: a multi-GPU machine, or a heavily compressed build with a lot of system memory. Not a laptop model.

Read the license first: Free, but not open source. Meta's license adds an acceptable-use policy, a requirement to credit Llama in products built on it, and a separate license if your product passes 700 million monthly users. You also have to accept the terms on the model page before downloading.

Who’s Who connected to it

  • Yann LeCunFounded and led FAIR, Meta's AI research lab where the Llama models were built. He has since left Meta to start his own lab, so he is not behind the newest releases.
How to run it yourself

These are model weights: a file you download, plus a program from the first section of the Free AI Projects page to load it.

  1. Install a runner first — Ollama is the shortest route, llama.cpp if you want the engine itself.
  2. Open the model card on this card's link and read the license and the size before downloading anything.
  3. Pick the size that fits your machine: a smaller, more compressed file if you have 8GB of memory, a larger one if you have a graphics card.
  4. Download it the way the model card says, then load it in your runner and ask it something you already know the answer to.
  5. Check the answer quality yourself on your own work — benchmark numbers on a model card are the maker's own.
  6. Read the license before commercial use: some open-weight models restrict it.
Model cardOpen model weights you can download

Google DeepMind

Small, efficient models that handle images as well as text — useful on one machine.

What you need to run it: The 4-billion version runs on a laptop; the larger sizes want a GPU.

Read the license first: Free to use commercially, but governed by Google's own terms and a prohibited-use policy rather than an open-source license, and Google can update that policy. You must pass the same restrictions on to anyone you give the model to.

Who’s Who connected to it

  • Demis HassabisRuns Google DeepMind, the lab that trained and released Gemma.
How to run it yourself

These are model weights: a file you download, plus a program from the first section of the Free AI Projects page to load it.

  1. Install a runner first — Ollama is the shortest route, llama.cpp if you want the engine itself.
  2. Open the model card on this card's link and read the license and the size before downloading anything.
  3. Pick the size that fits your machine: a smaller, more compressed file if you have 8GB of memory, a larger one if you have a graphics card.
  4. Download it the way the model card says, then load it in your runner and ask it something you already know the answer to.
  5. Check the answer quality yourself on your own work — benchmark numbers on a model card are the maker's own.
  6. Read the license before commercial use: some open-weight models restrict it.
Model cardOpen model weights you can download

DeepSeek

A very large, strong reasoning model, released with open weights.

What you need to run it: Server-class hardware to run yourself. Most people use it through a hosted provider.

Read the license first: Two different licenses in one repository. The code is MIT; the weights carry DeepSeek's own agreement with use restrictions attached. If you are shipping something built on the weights, read that second file, not the first.

Who’s Who connected to it

  • Liang WenfengFounded DeepSeek, which trained and released this model.
How to run it yourself

These are model weights: a file you download, plus a program from the first section of the Free AI Projects page to load it.

  1. Install a runner first — Ollama is the shortest route, llama.cpp if you want the engine itself.
  2. Open the model card on this card's link and read the license and the size before downloading anything.
  3. Pick the size that fits your machine: a smaller, more compressed file if you have 8GB of memory, a larger one if you have a graphics card.
  4. Download it the way the model card says, then load it in your runner and ask it something you already know the answer to.
  5. Check the answer quality yourself on your own work — benchmark numbers on a model card are the maker's own.
  6. Read the license before commercial use: some open-weight models restrict it.
Model cardOpen model weights you can download

ComfyUI

GPL-3.0

Comfy Org

A node-based workspace for image and video models. The most capable free option, and the least beginner-friendly.

What you need to run it: A graphics card with 8GB or more for comfortable use. Expect a learning curve.

Read the license first: Copyleft: if you distribute a modified version, your changes have to be published under the same license.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/comfyanonymous/ComfyUI.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageImages and video

InvokeAI

Apache-2.0

Invoke

A more guided image-generation studio, with a proper canvas for editing rather than a node graph.

What you need to run it: An installer, plus a graphics card for reasonable speed.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/invoke-ai/InvokeAI.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageImages and video

Stable Diffusion web UI

AGPL-3.0

AUTOMATIC1111

The long-standing browser interface for Stable Diffusion models, with an enormous library of extensions.

What you need to run it: A graphics card, and patience with the setup.

Read the license first: Strong copyleft: offering a modified version as a service means publishing your changes.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageImages and video

FLUX.1 [schnell]

Apache-2.0

Black Forest Labs

A fast, high-quality image model whose weights are open, unlike its bigger siblings.

What you need to run it: A graphics card with around 12GB, or a compressed build on less.

Read the license first: Only the [schnell] version is Apache-2.0. The [dev] version is non-commercial and [pro] is API-only — check which one you downloaded before using an image for paid work.

How to run it yourself

These are model weights: a file you download, plus a program from the first section of the Free AI Projects page to load it.

  1. Install a runner first — Ollama is the shortest route, llama.cpp if you want the engine itself.
  2. Open the model card on this card's link and read the license and the size before downloading anything.
  3. Pick the size that fits your machine: a smaller, more compressed file if you have 8GB of memory, a larger one if you have a graphics card.
  4. Download it the way the model card says, then load it in your runner and ask it something you already know the answer to.
  5. Check the answer quality yourself on your own work — benchmark numbers on a model card are the maker's own.
  6. Read the license before commercial use: some open-weight models restrict it.
Model cardImages and video

Stable Diffusion XL

CreativeML Open RAIL++-M

Stability AI

The widely supported image model that most free tools and tutorials are built around.

What you need to run it: A graphics card with 8GB or more. Runs in ComfyUI, InvokeAI or diffusers.

Read the license first: A responsible-AI license, not a standard open-source one: it lists uses you agree not to put the model to, and you must pass those restrictions on to anyone you share it with.

How to run it yourself

These are model weights: a file you download, plus a program from the first section of the Free AI Projects page to load it.

  1. Install a runner first — Ollama is the shortest route, llama.cpp if you want the engine itself.
  2. Open the model card on this card's link and read the license and the size before downloading anything.
  3. Pick the size that fits your machine: a smaller, more compressed file if you have 8GB of memory, a larger one if you have a graphics card.
  4. Download it the way the model card says, then load it in your runner and ask it something you already know the answer to.
  5. Check the answer quality yourself on your own work — benchmark numbers on a model card are the maker's own.
  6. Read the license before commercial use: some open-weight models restrict it.
Model cardImages and video

Diffusers

Apache-2.0

Hugging Face

The Python library for running image, video and audio generation models in your own code.

What you need to run it: Python, and a GPU for anything beyond small tests.

Who’s Who connected to it

  • Clément DelangueCo-founded Hugging Face, the company that writes and maintains this library.
How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/huggingface/diffusers.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageImages and video

Whisper

MIT

OpenAI

The reference speech-to-text model: transcribes and translates audio in a long list of languages.

What you need to run it: Python. The small models run on a laptop CPU; the large one wants a GPU.

Who’s Who connected to it

  • Sam AltmanRuns OpenAI, which published Whisper. The model is its research team's work.
How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/openai/whisper.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSpeech, transcription and voice

whisper.cpp

MIT

ggml / Georgi Gerganov

Whisper rewritten to run fast on ordinary machines, including phones and older laptops.

What you need to run it: A terminal and a model file. No Python, no GPU.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/ggml-org/whisper.cpp.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSpeech, transcription and voice

faster-whisper

MIT

SYSTRAN

A much faster Whisper that uses far less memory — the practical choice for batches of recordings.

What you need to run it: Python, and a GPU if you want the full speed benefit.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/SYSTRAN/faster-whisper.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSpeech, transcription and voice

WhisperX

BSD-2-Clause

Max Bain

Whisper with accurate word-level timings and speaker separation — who said what, and exactly when.

What you need to run it: Python and a GPU. Speaker separation needs an extra model you accept terms for.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/m-bain/whisperX.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSpeech, transcription and voice

Piper

MIT

Rhasspy

Fast local text-to-speech with a wide set of voices, good enough for narration and accessibility use.

What you need to run it: A small download. Runs on a Raspberry Pi, never mind a laptop.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/rhasspy/piper.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSpeech, transcription and voice

Coqui TTS

MPL-2.0

Coqui

A text-to-speech toolkit with many voices and languages, plus voice cloning.

What you need to run it: Python. A GPU for training your own voice; not needed just to speak text.

Read the license first: Weak copyleft — changes to their files must be shared, but your surrounding code stays yours. The company shut down, so the project is community-maintained now.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/coqui-ai/TTS.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSpeech, transcription and voice

OpenVoice

MIT

MyShell and MIT

Clones a voice from a short sample and speaks new text in it, across languages.

What you need to run it: Python and a GPU for sensible speed.

Read the license first: The license permits this; the law and basic decency still apply. Never clone a voice without that person's written permission.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/myshell-ai/OpenVoice.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSpeech, transcription and voice

Transformers

Apache-2.0

Hugging Face

The standard library for loading and running open models in Python.

What you need to run it: Python. Works on CPU for small models.

Who’s Who connected to it

  • Clément DelangueCo-founded Hugging Face, the company that writes and maintains this library.
  • Aidan GomezThis project is listed as their own work on their profile.
How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/huggingface/transformers.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageBuild something with it

PyTorch Foundation

The framework nearly every model here is built on.

What you need to run it: Python. GPU support is an extra install step.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/pytorch/pytorch.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageBuild something with it

LangChain

MIT

LangChain

Glue for chaining model calls, tools and data sources into an application.

What you need to run it: Python or JavaScript.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/langchain-ai/langchain.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageBuild something with it

LlamaIndex

MIT

LlamaIndex

Turns your own documents into something a model can answer questions over.

What you need to run it: Python, plus somewhere to store the processed text.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/run-llama/llama_index.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageBuild something with it

smolagents

Apache-2.0

Hugging Face

A deliberately small agent library — a few hundred lines you can actually read before trusting it.

What you need to run it: Python and a model, local or hosted.

Who’s Who connected to it

  • Clément DelangueCo-founded Hugging Face, the company that writes and maintains this library.
How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/huggingface/smolagents.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageBuild something with it

CrewAI

MIT

CrewAI

Runs several agents with defined roles that hand work to each other.

What you need to run it: Python. Costs add up quickly if you point it at a paid API rather than a local model.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/crewAIInc/crewAI.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageBuild something with it

BerriAI

One consistent way to call a hundred different model providers, so swapping model means changing one line.

What you need to run it: Python, or run it as a proxy server.

Read the license first: Everything outside the enterprise/ directory is MIT. That directory has its own commercial license, so check which features you are relying on before building a product around it.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/BerriAI/litellm.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageBuild something with it

LLaMA-Factory

Apache-2.0

hiyouga

Fine-tunes open models on your own examples through a web interface instead of training scripts.

What you need to run it: A GPU. You can rent one by the hour; a consumer card handles smaller models with efficient methods.

Read the license first: The tool is Apache-2.0, but the model you fine-tune keeps its own license — fine-tuning Llama does not free you from Meta's terms.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/hiyouga/LLaMA-Factory.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageBuild something with it

Unsloth

Apache-2.0

Unsloth AI

Makes fine-tuning and local running dramatically faster and lighter on memory.

What you need to run it: A GPU, though a modest one goes further than you would expect.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/unslothai/unsloth.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageBuild something with it

Hugging Face

Fine-tunes a large model by training a small add-on instead of the whole thing — the reason this is affordable at all.

What you need to run it: Python and a GPU.

Who’s Who connected to it

  • Clément DelangueCo-founded Hugging Face, the company that writes and maintains this library.
How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/huggingface/peft.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageBuild something with it

vLLM project

Serves an open model to many users at once, efficiently. What you use when a hobby project becomes a service.

What you need to run it: A GPU server. Not a laptop tool.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/vllm-project/vllm.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageBuild something with it

Hugging Face

Wraps a model in a usable web interface in a few lines, so you can hand it to someone non-technical.

What you need to run it: Python.

Who’s Who connected to it

  • Clément DelangueCo-founded Hugging Face, which acquired Gradio and now maintains it.
How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/gradio-app/gradio.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageBuild something with it

Chroma

A simple searchable store for text meaning, so a model can find the right passage of your documents.

What you need to run it: Python, and it will run inside your app with no separate server.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/chroma-core/chroma.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSearch, documents and data

Qdrant

A fast, production-grade search engine for the same job, when the collection gets large.

What you need to run it: Docker or a binary. Self-host it, or use their free hosted tier.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/qdrant/qdrant.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSearch, documents and data

FAISS

MIT

Meta AI Research

The underlying similarity-search library, when you would rather not run a database at all.

What you need to run it: Python or C++. A GPU build is available.

Who’s Who connected to it

  • Yann LeCunFounded FAIR, the Meta research lab that wrote and published FAISS.
How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/facebookresearch/faiss.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSearch, documents and data

Weaviate

A search database built for AI, with hybrid keyword-and-meaning search out of the box.

What you need to run it: Docker or Kubernetes.

Read the license first: The license file says plainly that different directories carry different terms. Most of it is BSD-3; some is under their own license. Check the directory your feature lives in.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/weaviate/weaviate.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSearch, documents and data

MarkItDown

MIT

Microsoft

Converts PDFs, Word files, spreadsheets and slides into clean text a model can read.

What you need to run it: Python, one command. Nothing else.

Who’s Who connected to it

  • Satya Nadellatheir company’s repository, not their own codeRuns Microsoft, which publishes this repository. The code is its engineers'.
How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/microsoft/markitdown.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSearch, documents and data

Tesseract OCR

Apache-2.0

Tesseract community (originally HP and Google)

Reads text out of images and scans, in over a hundred languages.

What you need to run it: An install, then one command per file.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/tesseract-ocr/tesseract.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSearch, documents and data

spaCy

MIT

Explosion

Pulls names, organizations, dates and structure out of text without needing a large model at all.

What you need to run it: Python. Runs fine on a CPU and is very fast.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/explosion/spaCy.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageSearch, documents and data

Composer by DXOS — Local-First Collaborative Workspace

License not checked yet — read it in the repository

DXOS

A local-first workspace from DXOS combining documents, spreadsheets, tables, and sketches with real-time peer-to-peer collaboration, custom plugins, custom functions, and AI agent workflows. Data syncs between devices without centralized servers. Composer is in early access; the product site and documentation are free.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryEntrepreneurship & Free Tools

MoltBot

License not checked yet — read it in the repository

MoltBot

Open-source personal AI assistant that runs locally on your own devices and connects to WhatsApp, Telegram, and Discord. Features persistent memory, proactive notifications, and community-built skill extensions. Formerly known as ClawdBot. Free and open source.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI Tools & Open Source

nilbuild/video-demo

License not checked yet — read it in the repository

nilbuild

Open-source skill that records video demos of your web app with zoom-ins and voiceover.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/nilbuild/video-demo.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

nimble — Local Typed Decisions

License not checked yet — read it in the repository

Bespoke Labs

Bespoke Labs' open-source toolkit for local typed decisions, contrastive data curation and model evaluation.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/bespokelabsai/nimble.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI Tools & Open Source

laya — Non-Autoregressive Decision Engine

License not checked yet — read it in the repository

Nandha Kishor M on GitHub

Open-source "System 1" decision engine: typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/NandhaKishorM/laya.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI Tools & Open Source

kev — Trainable Decision Models

License not checked yet — read it in the repository

Jared Palmer on GitHub

A Jev-like family of small decision models built on Qwen that you can train and run on your own hardware, from Jared Palmer.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/jaredpalmer/kev.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI Tools & Open Source

Conceptual Search: A Generative View of Entrepreneurial Imagination (Code and Data)

License not checked yet — read it in the repository

GitHub

Code and search records for a 2026 Strategic Entrepreneurship Journal paper that uses an AI model to evolve real startup concepts.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/fcsaszar/conceptual-search.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

NARCBench: Detecting AI Agent Collusion

License not checked yet — read it in the repository

Aaron Rose (GitHub)

Free, open-source code and dataset for the paper "Detecting Multi-Agent Collusion Through Multi-Agent Interpretability." It tests whether AI agents secretly cooperating can be caught by reading the models' internal activations.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/aaronrose227/narcbench.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.

Xiaomi MiMo

MIT — named by the project, not yet read here

Xiaomi

Xiaomi's open-weight AI model family — text, image, video, and audio understanding — released under the MIT license, free to download and self-host.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

Strands Agents Harness SDK (GitHub)

License not checked yet — read it in the repository

Strands Agents

Open-source SDK, Python and TypeScript, for building production AI agents you run yourself — any model, any cloud.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/strands-agents/harness-sdk.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

BigDiskBuster (Windows Defender DoS proof-of-concept)

License not checked yet — read it in the repository

MSNightmare (GitHub)

Public proof-of-concept for a Windows Defender update denial-of-service vulnerability. Fills the disk by triggering repeated definition updates.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/MSNightmare/BigDiskBuster.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.

Powermove

License not checked yet — read it in the repository

Powermove

Free open-source video and motion editor for Apple Silicon Macs. Connect a coding agent (Claude Code, Codex) to rewrite panels, effects, and extensions inside the running app.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

Open Measures Research

License not checked yet — read it in the repository

Open Measures

Research reports on how harmful content, extremism, and coordinated campaigns spread across social platforms. Public app and API are free (rate-limited to 39 requests per day, data 6 months old).

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.

pyLoad

License not checked yet — read it in the repository

pyLoad

Free, open-source download manager written in Python, managed entirely through a web interface. Lightweight enough to run on a home server, NAS or router, with plugins to automate repetitive downloads.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

yt-dlp

License not checked yet — read it in the repository

yt-dlp

Free, open-source command-line tool for downloading video and audio from thousands of sites. Actively maintained on GitHub, runs on Windows, macOS and Linux, and is the tool most other download apps wrap.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/yt-dlp/yt-dlp.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

HELM (open source framework on GitHub)

Apache-2.0 — named by the project, not yet read here

Stanford CRFM

The Python framework behind Stanford's HELM leaderboards, released under the Apache License 2.0 (licence file read, not copied from a roundup). You install it with pip, describe a run (scenario plus model plus metrics), and it evaluates the model and produces the same structured results the public site displays, including its own local web UI for viewing them. It supports hosted model APIs and locally run open-weight models, and you can add your own scenario to test a model on your own task or data. Free to use, modify and use commercially under Apache 2.0; you pay only for whatever model API calls or compute your own runs consume.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/stanford-crfm/helm.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.

OpenHarness

License not checked yet — read it in the repository

Autonomous AI

An open-source platform for running coding agents such as Claude Code and Codex across your own machines and specialising them for domains like CAD, PCBs, robotics and games, with optional open hardware.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/autonomous-ai/openharness.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Tabby Terminal

License not checked yet — read it in the repository

Tabby

A free, open-source terminal for SSH, local shell, and Telnet with modern tabs, splits, and theming.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryCareer & Professional Optimization

GitLab

License not checked yet — read it in the repository

GitLab

The intelligent orchestration platform for DevSecOps, enabling teams and agents to ship trusted software at enterprise scale.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

elizaOS (open source)

License not checked yet — read it in the repository

Open source framework for building AI agents, free to clone and run yourself.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/elizaOS/eliza.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

PyRIT

License not checked yet — read it in the repository

Microsoft

Microsoft's open-source toolkit for red-teaming AI systems: automated attack prompts, scoring of the responses, and repeatable runs. Free.

Who’s Who connected to it

  • Satya Nadellatheir company’s repository, not their own codeRuns Microsoft, which publishes this repository. The code is its security team's.
How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/Azure/PyRIT.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Inspect

License not checked yet — read it in the repository

UK AI Security Institute

An open-source framework from the UK's AI Security Institute for evaluating models — writing tests, scoring answers and logging what happened. Free.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

garak

License not checked yet — read it in the repository

NVIDIA

An open-source scanner that probes a language model for weaknesses — prompt injection, data leakage, jailbreaks, toxic output — and reports what it found. Free.

Who’s Who connected to it

  • Jensen Huangtheir company’s repository, not their own codeCo-founded NVIDIA and runs it; garak is published by its security team, not by him.
How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/NVIDIA/garak.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

AI Fairness 360

License not checked yet — read it in the repository

IBM / Linux Foundation AI

An open-source library of metrics and algorithms for finding and reducing unwanted bias in datasets and models, in Python and R. Free.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/Trusted-AI/AIF360.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

promptfoo

License not checked yet — read it in the repository

promptfoo

An open-source tool for testing and red-teaming prompts and AI apps — run the same prompts across models, compare answers, and catch regressions. Free and self-hosted.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

LibreOffice

MPL-2.0 — named by the project, not yet read here

The Document Foundation

A free, open-source office suite that opens and saves Word, Excel and PowerPoint files — a full replacement for a paid subscription.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryCareer & Professional Optimization

Stirling PDF

License not checked yet — read it in the repository

Stirling Tools

An open-source, self-hosted set of PDF tools — merge, split, sign, compress, convert — with no upload to somebody else's server.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/Stirling-Tools/Stirling-PDF.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryCareer & Professional Optimization

SearXNG

AGPL — named by the project, not yet read here

SearXNG

An open-source, self-hosted search engine that queries other engines without tracking you or building a profile. AGPL licensed.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/searxng/searxng.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Docling

MIT — named by the project, not yet read here

Docling project

An open-source tool that converts PDFs, Word files and scans into clean structured text for AI use, running locally. MIT licensed.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/docling-project/docling.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Aider

Apache-2.0 — named by the project, not yet read here

Aider

An open-source AI coding assistant that works in your terminal on a real git repository, making commits as it goes. Apache 2.0 licensed.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/Aider-AI/aider.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Continue

Apache-2.0 — named by the project, not yet read here

Continue

An open-source coding assistant for VS Code and JetBrains that you point at any model, including one running locally. Apache 2.0 licensed.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/continuedev/continue.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Dify

License not checked yet — read it in the repository

LangGenius

An open-source platform for building and running AI apps and agents, with a hosted option and a full self-hosted Docker install.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/langgenius/dify.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Flowise

Apache-2.0 — named by the project, not yet read here

FlowiseAI

An open-source drag-and-drop builder for chatbots and AI workflows you can run yourself and embed on a site. Apache 2.0 licensed.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/FlowiseAI/Flowise.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Langflow

MIT — named by the project, not yet read here

Langflow

An open-source visual builder for AI workflows and agents — drag components together, then export the flow as an API. MIT licensed.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/langflow-ai/langflow.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

n8n

License not checked yet — read it in the repository

n8n

A visual workflow tool for connecting apps and AI models — source-available, and free to run on your own server. Their hosted plans are paid.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/n8n-io/n8n.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Kilo — open source AI coding agent

License not checked yet — read it in the repository

Kilo

A free, open-source AI coding agent for VS Code, JetBrains, the command line and the cloud, with support for local models and your own API keys at no markup.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

Anaconda

License not checked yet — read it in the repository

Anaconda

The standard free Python distribution for data and AI work — package management, notebooks and thousands of libraries in one install.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

Pi

License not checked yet — read it in the repository

Pi

A terminal-based coding agent you run locally to read, write and refactor code from the command line.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

Hermes Agent

MIT — named by the project, not yet read here

Hermes Agent

A self-hosted, MIT-licensed AI agent with persistent memory that builds skills over time and reaches you on Telegram, Discord and other channels.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

OpenCode

License not checked yet — read it in the repository

OpenCode

A free, open-source AI coding agent that runs in your terminal, works with multiple model providers and can be installed with a single command.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

Herdr

License not checked yet — read it in the repository

Herdr

A free, open-source tool for running and monitoring multiple AI coding agents from one place, with a plugin ecosystem and documentation for the agent CLIs it supports.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

GitHub Resources and Guides

License not checked yet — read it in the repository

GitHub

GitHub's free article library explaining version control, DevOps, CI/CD, security practices and AI-assisted development in plain terms.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/resources/articles.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryCareer & Professional Optimization

GeoAI: Open Geospatial AI

MIT — named by the project, not yet read here

Open GeoAI

Free, MIT-licensed Python library and documentation for applying AI to satellite and geospatial data, with tutorials, notebooks, a QGIS plugin and video walkthroughs.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

Zed Code Editor

License not checked yet — read it in the repository

Zed Industries

A free, open-source code editor built in Rust for speed, with built-in AI assistance, real-time collaboration and multiplayer editing for pair programming.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

Claude Mods: Function Hooks Proposal (GitHub)

License not checked yet — read it in the repository

Anthropic

The public GitHub discussion where Anthropic and the community designed function hooks — a way for plugins to extend Claude Code — including the shipped design decisions and community feedback.

Who’s Who connected to it

  • Dario Amodeitheir company’s repository, not their own codeCo-founded Anthropic, whose repository hosts this thread. The proposal itself was written by someone outside the company.
How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/anthropics/claude-code/issues/91870.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Chroma (Open-Source Search & Vector Database)

Apache-2.0 — named by the project, not yet read here

Chroma

Apache 2.0 open-source search infrastructure for AI applications, supporting vector, full-text, regex and metadata search, free to run locally with optional hosted cloud.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

Matplotlib

License not checked yet — read it in the repository

Matplotlib

The open-source Python library for static, animated and interactive charts, with free plot-type galleries, tutorials, cheat sheets and a full API reference.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

ROOST: Open Online Safety Tools

License not checked yet — read it in the repository

ROOST

A nonprofit releasing free, open-source trust-and-safety building blocks so any platform can protect its users.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.

NVIDIA SkillSpector

License not checked yet — read it in the repository

NVIDIA

A free, open-source security scanner that checks AI agent skills and MCP servers for prompt injection, data exfiltration and supply-chain risks before you install them.

Who’s Who connected to it

  • Jensen Huangtheir company’s repository, not their own codeCo-founded NVIDIA, which publishes this.
How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/NVIDIA/SkillSpector.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.

DeepSeek Harness

License not checked yet — read it in the repository

DeepSeek AI

DeepSeek's free open-source agent harness, built on an "everything is a plugin" architecture, with a local web interface you can run in one command.

Who’s Who connected to it

  • Liang Wenfengtheir company’s repository, not their own codeFounded DeepSeek, which publishes this repository.
How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/deepseek-ai/deepseek-harness.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

SlopMonster

License not checked yet — read it in the repository

ItsssssJack

A free open-source tool that scores AI-written copy for tell-tale "AI voice", rewrites it with a rival model, then re-checks it, so landing pages, READMEs and emails read like a human wrote them.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/ItsssssJack/SlopMonster.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Inspo MCP

License not checked yet — read it in the repository

Nutlope

A free MCP server that gives coding assistants design taste, drawing on thousands of real websites captured with their palettes, fonts and layout structures.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

Archify

License not checked yet — read it in the repository

tt-a1i

A free agent skill that turns a codebase or a plain-English system description into an interactive architecture, workflow, sequence or data-flow diagram you can share as a single file.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/tt-a1i/archify.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Claudex Loop

License not checked yet — read it in the repository

chaseai-yt

A free Claude Code skill where two AI models harden a build plan before any code is written, then swap roles so whoever built it never grades it.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/chaseai-yt/claudex-loop.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

God's Eye View

License not checked yet — read it in the repository

Bilawal Sidhu

An open-source, browser-based "spy satellite simulator" that plots real satellites, planes, vessels and public cameras on a photorealistic 3D globe, and answers questions about the planet in plain language.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/bilawalsidhu/gods-eye-view.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

tldraw Chat Starter Kit

License not checked yet — read it in the repository

tldraw

A free working example of a chat app where you can draw to give an AI assistant visual context, with the code to build your own.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

OpenClaw

License not checked yet — read it in the repository

OpenClaw Foundation

An open-source personal AI assistant, run on your own device, that connects to chat apps like WhatsApp, Telegram, Slack, and Teams to handle email, calendars, and everyday tasks.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryAI & Assistive Tools

alpha-hunt

MIT — named by the project, not yet read here

mr-ravi26

An open-source (MIT) job-hunting automation tool that scans company career pages every 15 minutes, submits applications to applicant tracking systems when it is confident about a match, pulls wider market listings through the Adzuna jobs API, and sends alerts to Telegram.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/mr-ravi26/alpha-hunt.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryCareer & Professional Optimization

reveal.js

License not checked yet — read it in the repository

reveal.js

Free open-source framework for building presentations in the browser, with export and speaker notes.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryMarketing & Platform Tools

watermarks-remover (GitHub)

License not checked yet — read it in the repository

GitHub

Open-source project by Guillaume Meyer that strips multi-vendor AI provenance marks, including Unicode text artifacts, statistical rewrite hooks, and C2PA metadata from PNG, JPEG, SVG, PDF, DOCX, HTML, and Markdown files.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/guillaumemeyer/watermarks-remover.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.

Beancount.io — Plain-Text Accounting

License not checked yet — read it in the repository

Double-entry, plain-text accounting you can audit line by line. Web interface for the open-source Beancount ledger format — good for founders and freelancers who want real books without a subscription suite.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryEntrepreneurship & Free Tools

Generative AI for Beginners (Microsoft)

License not checked yet — read it in the repository

Microsoft

21 structured lessons on prompt engineering and building generative AI applications, with practical exercises in Python and TypeScript.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/microsoft/generative-ai-for-beginners.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Convert GitHub Actions to GitLab CI/CD (Free AI Skill)

License not checked yet — read it in the repository

Free AI skill that converts GitHub Actions workflows into GitLab CI/CD pipelines, usable from Cursor, VS Code, Claude, or any MCP-compatible client.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.
Project pageIts library entryMarketing & Platform Tools

career-ops: AI job search system on Claude Code

License not checked yet — read it in the repository

Open-source job search system with skill modes, a dashboard, PDF generation, and batch processing.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/santifer/career-ops.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

System Design Primer

License not checked yet — read it in the repository

Open-source guide to designing and scaling large web systems.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/donnemartin/system-design-primer.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.

FAANG Coding Interview Questions

License not checked yet — read it in the repository

Curated coding challenges pulled from real big-tech technical interviews.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/ombharatiya/FAANG-Coding-Interview-Questions.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.

The Algorithms

License not checked yet — read it in the repository

The web's largest open-source collection of algorithms across many languages.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.

Coding Interview University

License not checked yet — read it in the repository

Structured, free computer science study plan for landing engineering roles.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/jwasham/coding-interview-university.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.

Awesome Generative AI Guide

License not checked yet — read it in the repository

Open learning library with a 10-week applied LLM curriculum, 90+ free courses, and 60 AI interview questions.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/aishwaryanr/awesome-generative-ai-guide.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Job Search Agent (open-source AI job tracker)

License not checked yet — read it in the repository

Open-source AI agent that scans job boards daily, cross-references your LinkedIn network for warm intros, and emails you a curated list of matches. Self-hosted — you run it with your own keys.

How to run it yourself

This is source code you copy down and run on your own machine.

  1. Read the README on the project page first: it says what the project needs, and whether any part of it calls a paid service.
  2. Copy the code down: git clone https://github.com/evanzsolomon/job-search-agent.git
  3. Install what it depends on using the command in the README — usually npm install, pip install -r requirements.txt, or uv sync.
  4. Put any keys it asks for in a local .env file, and never commit that file.
  5. Run the start command from the README and use it locally on one small real task before you point it at anything that matters.
  6. Read the license before you use it for paid work — it is linked on this card.
Project pageIts library entryAI & Assistive Tools

Reactive Resume (rxresu.me)

License not checked yet — read it in the repository

Free, open-source resume builder with multiple templates, ATS-friendly exports, custom sections, and no paywall or watermark. Self-hostable if you want full control of your data.

How to run it yourself

This one starts from its own site, so the setup route is theirs, not a clone command.

  1. Open the project site and find its documentation or repository link.
  2. Decide which way you want it: their hosted free tier, or running it yourself from the source.
  3. For the hosted route, make an account and read where the free tier stops before you rely on it.
  4. For running it yourself, follow the install steps in their own docs — they change often enough that copying them here would go stale.
  5. Try it once on a real task of your own before building anything around it.

A license summary is not legal advice. If money depends on it, read the license file itself — every card links to it where it has been checked.