Verified project record
abhigyanpatwari/GitNexus
GitNexus indexes Git repositories or ZIP files into a precomputed knowledge graph using Tree-sitter, exposing structural context through 17 MCP tools or a browser-based UI. It supports AI coding agents by providing dependencies, call chains, and execution flows in a single query rather than requiring interactive exploration.
Project overview
By shifting codebase relationship extraction to index time, the project reduces the multi-turn exploration overhead that LLM-based agents typically face when navigating complex codebases.
- Project type
- MCP · AI Coding · RAG
- Use cases
- Knowledge Q&A · Coding & Development
- Deployment
- Refer to project documentation
- License
- License pending
Best for
- Developers who use MCP-compatible AI coding agents and need structural code context such as dependency tracking and call chain analysis.
- Teams looking to generate repository documentation directly from structural code analysis.
Key capabilities
- Parses codebases using Tree-sitter to extract dependencies, call chains, and execution flows into a structured knowledge graph.
- Precomputes clustering, tracing, and scoring operations at index time so AI tools return complete context in a single call.
- Provides 17 MCP tools for code intelligence, accessible via a local MCP server.
- Provides a visual graph explorer and AI chat interface in the browser.
- Generates repository wiki documentation directly from the knowledge graph.
- Installs exploration, debugging, and refactoring skills to the .claude/skills/ directory automatically.
- Supports re-indexing only changed files instead of the entire codebase to reduce update overhead.
Limitations and risks
- The browser-based Web UI is limited by browser memory and handles approximately 5,000 files; backend mode is required for larger codebases.
- Generating wiki documentation requires an external LLM API key such as OPENAI_API_KEY.
- GitNexus has no official cryptocurrency, token, or coin; any token using the name is unaffiliated.
Getting started
- Access the visual graph explorer and AI chat interface directly in the browser without installation.
- Run npx gitnexus analyze to index the codebase, and run npx gitnexus setup to configure MCP server integrations.
Alternatives and comparisons
- Turn any folder of code, docs, or media into a queryable knowledge graph with deterministic AST parsing and transparent connection tagging.
- Parses a multi-language codebase with Tree-sitter into a knowledge graph to query, edit, and optimize code using natural language and AST patterns.
- Cuts AI code-reading token costs by indexing codebases via tree-sitter AST and retrieving exact symbols instead of entire files.
Project comparisons
Evidence and sources
- GitHub project description: GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or ZIP file, and get an interactive k…
- README: Indexes any codebase into a knowledge graph — every dependency, call chain, cluster, and execution flow — then exposes it through smart MCP tools so AI agents never miss code.
- README: Tools like **Cursor**, **Claude Code**, **Codex**, **Cline**, **Roo Code**, and **Windsurf** are powerful — but they don't truly know your codebase structure.
- README: GitNexus **precomputes structure at index time** — clustering, tracing, scoring — so tools return complete context in one call:
- Release: v1.6.9
AI Search
Find projects, verify facts, compare options, or turn a complex need into an actionable plan
Try a searchA click only fills the search box; you stay in control
Project Details
0