guilds.run

guilds.run is an open-source platform for multi-agent AI agent teams. Unlike black boxes, guilds.run shows you the exact prompt, every tool call, and every memory change, so you don't have to trust — you can just verify.

Every run keeps the full record: the exact prompt the model saw, every tool call with its result, every memory change, and who wrote each note. That's how you get to a workflow you can leave running. Studio helps you tune the whole team: it reads your live runs, notes, memory, and schedules, finds why something keeps going wrong, and drafts the fix.

guilds.run supports any model: Claude, GPT, Gemini, Grok, or open-weight models like Qwen and Llama. Each agent can run a different one. Bring your own keys. Includes shared tables agents read and write, versioned notes and memory, and scripts agents write and run again.