formal verification

MathCode is a terminal AI coding agent for mathematical formalization: it turns plain-language math problems into Lean 4 theorems and attempts formal proofs, with a persistent Lean REPL and supporting theorem/axiom libraries.

A benchmark for coding agents that tests whether they can formally verify properties of real-world Rust web apps in Lean 4. It includes upstream code, i5h ports, extracted Lean models, proof attempts, and task-by-task results.

A Lean 4 project for formally verified 3D mesh intersection and constructive solid geometry, with a browser demo for intersecting example meshes or STL imports.

A capability-based microkernel written in SPARK Ada and formally verified with gnatprove, with a thin C SDK for building services and distribution components.

A Python filter layer for LLM apps that evaluates responses against a Lean-verified Scherf logic backend and can pass, flag, correct, or block output.

An autonomous neuro-symbolic formal verification engine for Lean 4. The repository describes a proof workflow that generates tactics and then checks them deterministically in Lean, with example proofs, verification steps, and telemetry outputs.

Anthropic’s research post shows Claude proving security properties across 123 open-source libraries and discusses how LLMs can support formal verification workflows for real software.

A Prove Together problem page for the Berge–Fulkerson conjecture, with a formal Lean target, provenance notes, reusable lemmas, and discussion around agent-assisted proof work.