⬢github TypeScript · 136 ★ +10 since we first saw it · pushed 4 h ago · NOASSERTION
AxiomCodeAI/axiomcodegraph
Turn any codebase into a knowledge graph grounded in formal methods. Your AI agents get exact answers for any code-related task, ensure correctness, and optimize time and token usage.
AxiomCode Graph builds a knowledge graph of a codebase using tree-sitter parsing and formal-methods-derived call relationships, so AI coding agents can query exact caller/callee information instead of grepping. It integrates via MCP with tools like Claude Code and Cursor, prunes irrelevant code to save tokens, and supports Python, TypeScript, Java, and more.
Why now: It was recently featured in a Show HN post claiming it reduces coding-agent rework with formal methods, alongside benchmark results on Defects4J test selection.
Who it is for: Developers using AI coding agents (Claude Code, Cursor, Codex, etc.) on medium-to-large codebases who want precise code context and fewer agent mistakes.
ai-agentsai-skillsantigravityastchange-impact-analysisclaude-codecode-analysiscode-searchcodegraphcodex
Stars over our 34 snapshots: 126 to 136, since 8 h ago.
Where people talked about it
API: https://socialmediatrends-api.osmike.com/v1/repos/AxiomCodeAI/axiomcodegraph