MathCode is a terminal AI coding assistant with a built-in math formalization engine. Give it a math problem in plain language and it will automatically convert it into a Lean 4 theorem and attempt a formal proof — with a persistent Lean REPL, reusable theorem and axiom libraries, agentic proving, and an Obsidian knowledge graph.
Requires macOS (arm64) or Linux (x86_64), plus the codex CLI for the default backend.
git clone https://github.com/math-ai-org/mathcode.git
cd mathcode
bash setup.sh
codex auth login
mathcodesetup.sh prepares the release checkout, downloads the bundled runtime and Lean toolchain, and installs a user-local mathcode launcher. Try it with:
mathcode -p "prove that the square of an even number is even"Outputs are written to LeanFormalizations/. A browser UI is available via ./run webui.
A persistent Lean language server brings compile checks to ~0.4s after a one-time warmup, instead of ~30s.
Every proved theorem is auto-named, stored, and made importable so the prover and planner can reuse it.
Store conversational assumptions as persistent, compile-checked, consistency-reviewed Lean declarations.
Searches leansearch.net and Loogle for verified Mathlib lemmas and uses structured LSP diagnostics for repairs.
Generates an Obsidian vault that visualizes theorem-to-lemma dependencies as a knowledge graph.
Each proof becomes an interactive session where the agent writes candidates, reads errors, and recompiles.
Decomposes complex theorems into independent subgoals and proves them in parallel, then stitches them back.
Runs multiple planners in parallel for diverse proof strategies; the prover picks the best approach.
If you use MathCode in research, please cite:
@misc{mathcode2026,
title = {MathCode: A Frontier Mathematical Coding Agent},
author = {Team Math-AI},
journal = {math-ai-org.github.io},
year = {2026},
month = {April},
url = {https://github.com/math-ai-org/mathcode}
}The math formalization and proving pipeline is based on the AUTOLEAN project.