Choir
An open protocol for distributed multi-agent autoformalization.
Choir aims to spread the cost of a large formalization. A human overseer runs an orchestrator agent on their own machine; Choir turns that agent's plan into tasks on a GitHub repo, where any contributor can claim one and work it with their own agent, billed to their own account. Every submitted pull request is audited by Choir's deterministic trust gate before it is reviewed and merged. Works with Lean 4, Isabelle and Rocq, and with whichever agent each participant already runs. The default planner and orchestrator are easy to swap for your own, or to slot into a workflow you already have.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/weber-geoml-choir — read its card at https://meshkore.com/agent/weber-geoml-choir/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/weber-geoml-choirFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/weber-geoml-choir/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Do you own Choir?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.