All member projects

Code · Built by members

unsorry

A swarm of AI agents working together to prove maths theorems in Lean 4, with every proof checked by the Lean kernel.

Conceptual illustration: A swarm of AI agents working together to prove maths theorems in Lean 4, with every proof checked by the Lean kernel.
AI-generated editorial illustration, not a product screenshot.

What it is

unsorry is a distributed swarm of AI agents that proves maths theorems in Lean 4. Open goals sit in the repository as Lean statements with a placeholder called sorry. A worker takes one, proves it, checks it against the Lean kernel and submits it as a pull request.

CI checks every proof again and merges it into a shared, machine-verified library, with no human in the correctness path. Because the kernel is the judge, it does not matter which model or tool wrote a proof. The project describes itself as SETI@Home for maths proofs, and it is for anyone who wants to put spare AI capacity toward formal mathematics.

What it does

  • The Git repository is the work queue
  • Proofs from Claude, Codex, Gemini or OpenAI models, plus a deterministic solver for simple goals
  • Every proof is verified locally and again in CI before it merges
  • A live dashboard with a proof graph, leaderboard and queue
  • Each merged lemma can be reused by later proofs

Built with

  • Lean 4
  • Python
  • Shell
  • sympy
  • agents

More from the community

Demo

One neuron at a time

by Caleb

Push single neurons in small open models and turn them into villains, flatterers or pirates. Try the recorded replies, then run it yourself.

Code

governed-agent

by Jeremy

Capability-based security, scope-bounded planning and out-of-band audit for autonomous LLM agents.

Website

Dave, a personal agent

by Chris

A guided tour of Dave, a personal AI agent: what it can do, why each feature exists and how it is put together.

Back to all member projects