lean-dojo
Machine Learning for Theorem Proving in Lean
Built from lean-dojo's public GitHub profile, United States of America. Not on Take My Repo yet, so there are no posts or updates here.
TorchLean is the first unified Lean 4 framework for neural-network specification, execution, and verification.
LeanDojo-v2 is an end-to-end framework for training, evaluating, and deploying AI-assisted theorem provers for Lean 4.
LeanAgent is a novel lifelong learning framework for formal theorem proving that continuously generalizes to and improves on ever-expanding mathematical knowledge without forgetting previously learned knowledge.
Arbitrary verified fast precision floating point arithmetic in Lean, with proofs, optimized backends, and support for IEEE binary and decimal, posits, and custom formats.
Formalization of the Millennium Problems in Lean 4
Structured runtime profiling for Lean4 code, with nested spans, Perfetto traces, regression checks, and optional TorchLean integration.
The first unified benchmark for quantum-science reasoning across informal natural-language solutions and Lean-oriented formal representations.
Guiding Search for Neural Theorem Proving via Proof Progress Prediction
ITPEval is a benchmark suite and evaluation framework for formal statement and proof translation across Lean 4, Rocq, Isabelle/HOL, and HOL Light
Lean proofs for the derivations in Singularity of the Euler Equations on R^3