Back to directory

GitNexus

A tool that indexes a codebase into a knowledge graph of dependencies, call chains and execution flow, then exposes it to AI coding agents through MCP.

GitNexus

GitNexus indexes a codebase into a knowledge graph that tracks dependencies, call chains, clusters and execution flow, then exposes that graph to AI coding agents through MCP tools so the agent has an architectural view of the code rather than working from isolated file reads. It is run from the command line: an analyze command indexes the repository, installs agent skills, registers hooks for Claude Code, and creates AGENTS.md and CLAUDE.md context files, while a setup command writes the MCP configuration each supported editor needs.

The project supports editors and agents including Cursor, Claude Code, Codex and others that auto-detect during setup, and it also provides a web UI for chatting with an indexed repository in the browser. It is written in TypeScript and distributed through npm.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.