Graph-Native Infrastructure for Context and Accountable AI Systems

Reference parser and interpreter for the Dogwood policy language

A Lean library for machine-checked cryptographic proofs.

DyLean, a framework for the symbolic analysis of cryptographic protocols

Type-Based and Trace-Based Symbolic Protocol Verification in Lean

Core cryptographic library for Windows, Azure Linux and other products

Lean 4 kernel / 'external checker' written in Lean 4

AI-assisted Lean project automation with DAG blueprints, proof orchestration, and multi-agent coding/proving workflows.

A library for composable state machines and cryptography

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Skills for Real Engineers. Straight from my .agents directory.

A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture

Git. Ship. Done - Core

Convert any Repo into an RL Environment

The official code release for REFACTOR: Learning to Extract Theorems from Proofs

Build structured Proof Blueprints with Verso

Lean 4 library for polynomial functors, interaction trees, and frameworks for modeling interactive and effectful protocols

Lean 4 tactic library for closing proofs across applied mathematics. Probability, statistics, biology, chemistry, economics, engineering, mechanics, control, queueing, info theory. Axiom-clean agai…

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…

The agent that grows with you

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

A programming language for AI orchestrations (POC)

Multi-party session-typed program environment

#1 Persistent memory for AI coding agents based on real-world benchmarks

The best-benchmarked open-source AI memory system. And it's free.