Home/AI Agents/LeanCopilot
LeanCopilot logo

LeanCopilot

lean-dojo/LeanCopilot

LLMs as Copilots for Theorem Proving in Lean

GraphCanon updated today · GitHub synced today

1.3k stars127 forksLast push 2d C++ MIT

Decision brief

A system that leverages large language models for theorem proving in the Lean environment.

Good fit when

  • Need support with formal proof development in Lean or Lean4 specifically
  • Seeking to enhance automated reasoning capabilities within a Lean project

Avoid when

  • Working exclusively in theorem provers other than Lean or Lean4
  • Looking for general-purpose AI programming assistant beyond Lean's domain

Observed Jul 17, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Very active (2d since push)
As of today
Provenance
Not a fork · Organization account
As of today
Security (OSV)
No lockfile
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

git clone https://github.com/lean-dojo/LeanCopilot

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

A system that employs large language models to assist with theorem proving within the Lean formalization environment, supporting both Lean and Lean4.

Capability facts

Deploy
Self-host

Source: dockerfile:Dockerfile · Aug 25, 2026

Docker
Dockerfile present

Source: dockerfile:Dockerfile · Aug 25, 2026

Languages
c++

Source: github.language · Aug 25, 2026

Categories

Tags

README

Requirements

  • Supported platforms: Linux (priority), macOS (priority), Windows and Windows WSL.
  • Git LFS.
  • Optional (recommended if you have a CUDA-enabled GPU): CUDA and cuDNN.
  • Required for building Lean Copilot itself (rather than a downstream package): CMake >= 3.7 and a C++17 compatible compiler. A downstream package normally downloads a prebuilt release instead of needing these, except on a platform we don't publish a release for (e.g. Intel macOS), where it automatically falls back to building from source and so needs them too.

Getting Started with Lean Copilot

Tactic Suggestion

After import LeanCopilot, you can use the tactic suggest_tactics to generate tactic suggestions. You can click on any of the suggested tactics to use it in the proof.

suggest_tactics

You can provide a prefix (e.g., simp) to constrain the generated tactics:

suggest_tactics_simp

Proof Search

The tactic search_proof combines LLM-generated tactics with aesop to search for multi-tactic proofs. When a proof is found, you can click on it to insert it into the editor.

search_proof

Premise Selection

The select_premises tactic retrieves a list of potentially useful premises. Currently, it uses the retriever in LeanDojo to select premises from a fixed snapshot of Lean and mathlib4.

Running LLMs

You can also run the inference of any LLMs in Lean, which can be used to build customized proof automation or other LLM-based applications (not limited to theorem proving). It's possible to run arbitrary models either locally or remotely (see Bring Your Own Model).

run_llms

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.