Permanent code intelligence layer. Learns what matters, expires what changed, proves what existed. Content-addressed graph with Merkle proofs, 25 extractors, 23 MCP tools. Gets smarter with use.

GitHub Action to generate architecture documentation for any repository using Supermodel

A persistent structural knowledge graph for codebases. Lets AI coding agents and developers query symbols, references, and call chains via MCP tools and a CLI tree explorer.

Code knowledge graph — Tree-sitter parsing, SQLite storage, BFS traversal. Powers Prism; embeddable Go API, CLI, and MCP. MIT licensed.

Journey-first graph for agent memory. MCP-native context for OpenCode.

A codebase onboarding and verification assistant for developers and AI agents. Single-binary CLI and MCP server providing code graphs, data-flow tracing, impact analysis, and guided walkthroughs.

codegraph is a local-first code context engine and MCP server for repositories. It incrementally indexes source code into a lightweight SQLite graph, then exposes high-signal tools for symbol lookup, call graph traversal, impact analysis, related test discovery, and semantic search. Built in Go with a single-binary workflow, it is designed to work

Agentic terminal AI assistant with a Bubble Tea TUI, code-graph review, semantic search, multi-provider LLMs, and MCP tools.

Semantic code map and code graph MCP server for AI coding agents, powered by SCIP and Tree-sitter.

Turn any repo into a queryable code graph your AI assistant reads instead of grepping. One static Go binary — zero API keys, $0, fully offline, deterministic.