Every Project Is Readable
Each entry links straight to its repository, so you can read the code and judge the thing before you commit an afternoon to it.
Several specialised agents coordinating on one job with shared state.
Try removing a filter or searching for something else.
Every entry is open source, currently maintained, and documented well enough to start from.
Each entry links straight to its repository, so you can read the code and judge the thing before you commit an afternoon to it.
Languages, frameworks and infrastructure are listed per project — not left as "some AI" — so you know what you are signing up to run.
Beginner through expert, set against what the project actually asks of you: the toolchain, the hardware and the prerequisites.
MIT, Apache, AGPL or something bespoke — stated on the card, because it decides whether you can ship what you build.
Filter to what runs on your own hardware, or to what only needs a key. Both are legitimate; the catalogue does not assume.
Category, technology and tag hubs cross-cut the same catalogue, so you can arrive from whichever direction you already think in.
Every project in Multi-Agent Systems is open source and buildable — each one links straight to its repository so you can read the code before you commit an afternoon to it.
Still stuck? Our team answers every message.
Still have a question? We usually reply within one working day. Report Issues A broken tool or a missing page? Tell us. Submit your AI tool Add your AI tool to our directory.We use cookies to enhance your browsing experience, analyze site traffic, and personalize content.
You can change your cookie preferences anytime. Learn more