A home cluster that tries to prove theorems.
Small AI models running on secondhand graphics cards write proofs. The Lean 4 proof checker reads every one and says yes or no. It never takes the model's word for anything.
The lab, live
These numbers come from the cluster itself and refresh every 15 seconds. The lab pushes them out; nothing on the internet can reach in.
Fresh from the checker
The newest proofs Lean accepted, exactly as the model wrote them. New ones appear here as they land.
The graphics cards
Each card: temperature now, load bar, and temperature over the last 3 hours on a fixed 20 to 100 °C scale. Hover a line for values.
The cluster runs behind a battery power station fed by solar panels, which is why leaving a proof search running for weeks is affordable.
Guess, check, repeat. For as long as it takes.
A language model can write something that looks like a proof and is wrong. Lean cannot be talked into anything: a proof either compiles or it does not. Put the two together and a wrong answer costs nothing but time.
So the lab takes one small lemma at a time, asks a local model for a proof, and hands it to Lean. A failure comes back with the exact error, and the model tries again with that error in hand.
Below is the checker answering four real submissions from the lab's test suite: a good proof, a false statement, a placeholder, and an attempt to cheat with a made-up axiom.
Two small models, 20 lemmas, 40 proofs
The first benchmark: 20 easy statements, from a + b = b + a to 2ab ≤ a² + b². Each model got up to four tries per lemma, with Lean's error message handed back after a miss.
Both are open models built for Lean, running on 4 GB graphics cards from 2016. The model only writes the proof; the statement is fixed, so it cannot pass by changing the question.
Five roles, one rule
Nothing counts as proved unless Lean compiled it with no placeholders and no added axioms.
Where the build stands
- 1✔ done
Lean worker
A container that compiles any Lean file against Mathlib and answers in about 3 seconds.
- 2✔ done
Model workers
Two Lean-specialised models were benchmarked on 20 easy lemmas. Each solved all 20, with Lean checking every proof.
- 3◐ testing
Orchestration
The unattended loop is running, with n8n as the foreman. Now on its 48-hour test: no stalls allowed.
- 4○ planned
Real targets
A backlog of results that are known but not yet in Mathlib, Lean's public maths library.
- 5○ planned
Open to contributors
Public lemma backlog and proofs, with every outside submission verified away from the home network.
Learn Lean. Put old hardware to work.
Learn Lean 4
The best way to learn a proof language is to build something that speaks it all day, and read what the checker says back.
Give e-waste a second life
Retired office PCs and graphics cards from 2016, bought secondhand, running proof search around the clock on solar power.
Grind small lemmas
Many small, well-defined statements, tried over and over, with a referee that rejects every wrong answer for free.