The personal site and blog of a Toronto-based open source developer known for Amfora, a terminal browser for the Gemini protocol, and for image dithering tools (dither, didder, Dithertime). Posts cover small-internet protocols, open source projects, voting systems, and software design. Free to read.
Why I recommend it: A good example of the "small web" corner of the internet: one person, useful open source tools, thoughtful writing. Follow if you are interested in protocols and software outside the big platforms.
Read / subscribe freeThis is the only entry from makeworld.space — Personal Site and Blog in the hub so far.
Other resources that share this publication's topics.
A KDnuggets article by Shittu Olumide describing seven open models under 10 billion parameters, each built for one task such as transcription, OCR, routing or speech, and comparing them with much larger general-purpose models. Performance claims come from the models' publishers and cited benchmarks.
An open GitHub repository from Jane Street with agent skills for AI coding assistants, including a Socratic tutor skill, published with a license and contribution guide.
Ace is an experimental local collaboration tool for building software with AI agents and teammates on Macs connected through Tailscale. The documentation describes channels, team-hosted infrastructure, bring-your-own model keys and the security implications of agents running with the host user's privileges.
Why I recommend it: MIT-licensed software. Setup requires Tailscale and an Anthropic or OpenAI API key; model-provider and optional hosting costs may apply.
Hayden Bleasel discusses open-source maintenance and argues that its value extends beyond code, even as AI agents make reproducing software easier. A free essay about software development and maintainers.
A public collection of coding-agent skills, including Stageshow for creating React product-interface illustrations and demos. Each skill has its own license and third-party asset notices, which should be checked before reuse.
A Claude Code and Codex skill for auditing AI-generated interfaces, proposing a design direction, and refining screens. The repository uses CC BY 4.0, requiring attribution; optional image services may cost money.
