gitnexus vs codegraph
Two of the top projects in MCP servers for developers, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
gitnexus
Code knowledge graph exposed to coding agents through MCP tools
codegraph
Local code knowledge graph served to coding agents over MCP
Verdict
gitnexus ranks higher, 89 to 81. Of the 5 score parts we measure for both, gitnexus leads on 3, codegraph on 1 and 1 is even.
- Adoptioncodegraph leads by 17 points, 94 to 77: a wide gap.
- FreshnessEven at 100.
- Maintenancegitnexus leads by 3 points, 92 to 89: close to even.
- Easy to rungitnexus leads by 33 points, 83 to 50: a wide gap.
- Agent-readygitnexus leads by 15 points, 100 to 85: a wide gap.
Pick gitnexus if you are
Developers giving Claude Code, Cursor or Codex repo-wide dependency context
- Precomputes clusters and processes at index time, so impact returns callers and confidence in one call
- One analyze command indexes, installs skills, registers Claude Code hooks and writes AGENTS.md/CLAUDE.md
Pick codegraph if you are
Developers using AI coding agents on mid-to-large codebases
- Runs locally; no Node.js needed, ships as a bundled installer or npm package
- One `codegraph install` configures MCP for nine named agents and IDEs
| What we compare | gitnexus | codegraph |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 77, popular | 94, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | 92, healthy | 89, healthy |
| Easy to run | 83, very easy | 50, easy |
| Agent-ready | 100, ready | 85, ready |
| Facts from GitHub and the README | ||
| Stars | 47.9k | 74.1k |
| License | custom license (read the license) | MIT (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Sep 2026 | Oct 2026 |
| Language | TypeScript | C |
| Docker | Yes | No |
| GPU | Optional | Not needed |
| arm64 or Apple Silicon | Mentioned | Mentioned |
gitnexus
GitNexus indexes a repository with Tree-sitter into a LadybugDB graph of dependencies, call chains, clusters and execution flows. It serves that graph to agents such as Claude Code, Cursor and Codex through 19 MCP tools (impact, trace, query, rename, cypher and others), and installs skills and hooks. A browser Web UI offers graph exploration and chat.
Who it is for: Developers giving Claude Code, Cursor or Codex repo-wide dependency context
Strengths
- Precomputes clusters and processes at index time, so impact returns callers and confidence in one call
- One analyze command indexes, installs skills, registers Claude Code hooks and writes AGENTS.md/CLAUDE.md
- setup auto-detects editors; Claude Code and Codex get MCP, skills and pre/post tool hooks
- CLI indexing runs locally with native Tree-sitter and persistent LadybugDB storage
Weaknesses
- PolyForm Noncommercial license restricts commercial use
- Web UI in-browser mode is limited to about 5k files
- npx install can crash on npm 11; some grammars need a C++ toolchain or are skipped
- Render deploy costs about $35/month and the token is the only access control
- GPU optional
- Docker + Compose
- Needs Node.js, LadybugDB, Tree-sitter
- Models: Claude Code, Cursor, Codex, Antigravity, Windsurf
codegraph
CodeGraph indexes a project into a local graph of symbols, call edges and dependencies under `.codegraph/`, then exposes it to coding agents through an MCP server. Agents can fetch relevant source, call paths and change impact in one call instead of grepping and reading files. `codegraph install` wires it into Claude Code, Cursor, Codex CLI, opencode, Gemini CLI, Kiro, GitHub Copilot and others, and auto-sync keeps the index current.
Who it is for: Developers using AI coding agents on mid-to-large codebases
Strengths
- Runs locally; no Node.js needed, ships as a bundled installer or npm package
- One `codegraph install` configures MCP for nine named agents and IDEs
- Covers 30+ languages, including TypeScript, Python, Go, Rust, Java, C#, Swift
- Watches files and updates the graph automatically; no manual re-index
Weaknesses
- README admits about 80% more retrieval context stays resident in long sessions
- Published benchmarks are the author's, on 7 repos with one question each
- No Docker or compose setup; install is via curl/PowerShell script or npm
- Hosted CodeGraph platform is a waitlist product, separate from this repo
- no GPU
More in MCP servers for developers
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.