Coding assistants
Herdr
Made by Herdr
Free, Apache-licensed software for running several agents on one job at once.
What it is
Herdr coordinates multiple agents instead of running a single assistant — you give it a job and it splits and supervises the work.
The interesting use for most people is comparison: set several models the same task and watch how differently they approach it. That teaches you more about model choice than any leaderboard.
The software is free under Apache 2.0 and there is nothing to buy. You pay only for whatever model keys you use.
Published price
- HerdrApache 2.0, installed and run by you$0
- Model useWhatever your own API key costs
Herdr has no pricing page — there is nothing to buy from them.
Source: the Herdr site · Last checked 17 September 2026
Benchmarks
The published figures for Herdr, copied exactly as their sources give them and checked 17 September 2026. Each one names the test, who ran it and when, and says when the number comes from the maker rather than an independent tester.
No published score. Herdr isn't a model — it runs several agents side by side, so there's no capability score to publish. The only figures its site quotes are speed and processor use against tmux, which measure the terminal, not the AI. A benchmark for this kind of orchestration now exists (ClawArena-Team, July 2026), but nobody has run Herdr on it, so there is still nothing to quote.
Where to read today's numbers
Scores move, so these are the boards that keep them current.
- SWE-bench leaderboardIndependent
Measures whether an agent can fix real GitHub issues. The standard reference for coding agents.
- OpenRouter rankingsIndependent
Ranks models by how much real developer traffic they actually get — usage, not quality.
How it performs, in my experience
Coordinates several agents on one job instead of running a single assistant.
Free value
5 / 5
How much you get without paying.
Performance
3 / 5
How well it does its main job.
Range of uses
2 / 5
How many different jobs it suits.
Free and open; useful mainly if you want several agents on one job. These scores are my own judgment, not a measurement — the benchmark links above are the independent version.
Prompting it from this site
Can't be run from here
A runtime that keeps other agents alive in terminals; there's no model here to prompt.
Use it for
- Running more than one agent at once
- Comparing how models tackle the same task
Running it yourself
Hosted only — nothing to install
Herdr is a hosted service with no published weights or self-hosted build, so it can't be run locally.
What you need first
- An account on their site
Step by step
1.Use it in the browser — nothing to install