lean-dojo/LeanDojo-v2
LeanDojo-v2 is an end-to-end framework for training, evaluating, and deploying AI-assisted theorem provers for Lean 4.
This framework helps mathematicians and logicians working with Lean 4 to build and deploy AI systems that can assist in proving theorems. It takes Lean repositories as input, extracts structured theorem information, and then trains AI agents to propose or verify proofs. The output is an AI-assisted theorem prover that can help solve complex mathematical problems.
Use this if you are a formal verification researcher or mathematician using Lean 4 and want to leverage AI to automate or accelerate theorem proving.
Not ideal if you are looking for a pre-trained, off-the-shelf theorem prover without needing to train or fine-tune models yourself.
Stars
48
Forks
10
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lean-dojo/LeanDojo-v2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
nschaetti/EchoTorch
A Python toolkit for Reservoir Computing and Echo State Network experimentation based on...
metaopt/torchopt
TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
gpauloski/kfac-pytorch
Distributed K-FAC preconditioner for PyTorch
opthub-org/pytorch-bsf
PyTorch implementation of Bezier simplex fitting
pytorch/xla
Enabling PyTorch on XLA Devices (e.g. Google TPU)