lean-dojo / LeanDojo-v2

LeanDojo-v2 is an end-to-end framework for training, evaluating, and deploying AI-assisted theorem provers for Lean 4.

Why this job: works in the areas we cover, but does not say which job it does

What it does

Unified Agent Abstractions. BaseAgent orchestrates repository setup, training, and proving. Concrete implementations (HFAgent, LeanAgent, and ExternalAgent) tailor the workflow to Hugging Face models, retrieval-based provers, or REST-backed
Powerful Trainers. SFTTrainer, GRPOTrainer, and RetrievalTrainer cover LoRA-enabled supervised fine-tuning, group-relative policy optimization, and retriever-only curriculum learning.
Multi-Modal Provers. HFProver, RetrievalProver, and ExternalProver run on top of Pantograph’s Lean RPC server to search for tactics, generate whole proofs, or delegate to custom models.
Lean Tracing Pipeline. lean_dojo includes the Lean 4 instrumentation (ExtractData.lean) and Python utilities to trace commits, normalize ASTs, and cache proof states.
Dynamic Repository Database. database tracks repositories, theorems, curriculum difficulty, and sorry status, enabling lifelong training schedules.

Repos similar to this one
Repo	Stars	Last commit	Licence	Downloads for
augustepoiroux / LeanInteract	138	25 days ago	MIT	No downloads
stanford-centaur / PyPantograph	151	13 days ago	Apache-2.0	No downloads
fabio-rovai / open-ontologies	2,871	yesterday	MIT	Mac, Windows, Linux

More: languages, topics and project record