mache: Mache parses codebases to discover their structure and exposes it as a navigable graph via MCP tools or a filesystem mount. It allows agents to explore call chains, jump to definitions, and read context without grepping flat files. Built for AI agents, it provides stable node paths and identity-preserving write-back.; memtrace-public: Memtrace is a persistent memory layer for coding agents. It builds a bi-temporal, episodic, structural knowledge graph from your codebase's AST, enabling agents to remember and reason about code structure, evolution, and dependencies. It runs entirely locally, indexing code in seconds and providing sub-millisecond query latency.
Agent-based code exploration and navigation
Codebase exploration and understanding