Visualizing the network of math theories.
-
Updated
Jun 9, 2024 - Python
Visualizing the network of math theories.
OpenATP is an open-source Python package providing a common interface for Automated Theorem Proving (ATP)
Fast Lean 4 proof feedback for coding agents. CLI, Python library, and MCP server with warm LeanInteract sessions and cached env reuse.
Rights: License Copyright Ultra Verba Lux Mentis 2025. all rights reserved This repository is a reproducible research + governance scaffold that combines: Lean 4 formalization (machine-checked theorems; “hard-to-reject” anchors) Python reference implementations (toy experiments + benchmarks)
AI-native math collaboration platform — discussion + leaderboard for Lean 4 formalization agents
Lean 4 diagnostics and infoview output for LaTeX PDFs
OPEN PROBLEMS WANT TO STAY OPEN
Retrieval-grounded reviewer-memory tool over closed-PR review history of leanprover-community/mathlib4. Indexes ~158k past reviewer comments across ~35k closed PRs to flag concerns past reviewers have raised before.
Self-hostable paraconsistent HoTT LLM-to-Lean acceptance gateway. Runs proof attempts through security preflight, Lean checks, theorem-fingerprint locks, and ShadowHoTT bilattice routing for accept/repair/reject/human-review decisions.
Measure how far informal proofs are from Lean 4: structured readiness reports, mathlib alignment, and reproducible benchmarks.
Reproduction of Ax-Prover: a 3-agent LLM framework for automated Lean 4 theorem proving
Lean 4 / Mathlib v4.11.0 formalisation of the kernel dimension theory of the Z/2 connection Laplacian on finite simple graphs, with paper
A minimal, reusable CI template for running Lean 4 proofs on Morph Cloud's Infinibranch with intelligent caching and sharding.
MCP server for fast local Lean and Mathlib theorem search with tree-sitter indexing and proof probes
Trusted base of definitions, schemas, and verification artifacts for the Unified Rigidity Framework
Formally verified quantitative finance — Lean 4 proofs + Python/Cython execution
Experimental formal-methods framework for generating finite semantic path-equivalence theorem artifacts in Lean/Mathlib from Python witness records.
Live Lean v4.13.0 kernel for the Lutar Invariant — Λ uniqueness as Conjecture 1. 749/14/163, source-mirrored from HF Space SZLHOLDINGS/lean-kernel. Doctrine v11 LOCKED · Apache-2.0.
Mudra Recognition Model is a real-time computer vision system that detects and identifies Sattriya dance mudras using hand tracking. Built with MediaPipe and OpenCV, it analyzes hand landmarks to recognize gestures and display their meanings instantly, blending AI with cultural preservation.
Add a description, image, and links to the mathlib topic page so that developers can more easily learn about it.
To associate your repository with the mathlib topic, visit your repo's landing page and select "manage topics."