gitnexus vs code-review-graph
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
code-review-graph
Local Tree-sitter code graph that gives coding assistants review context over MCP
Verdict
gitnexus ranks higher, 96 to 92. Of the 4 score parts we measure for both, gitnexus leads on 3, code-review-graph on none and 1 is even.
- Adoptiongitnexus leads by 4 points, 94 to 90: close to even.
- FreshnessEven at 100.
- Maintenancegitnexus leads by 1 point, 94 to 93: close to even.
- Agent-readygitnexus leads by 30 points, 100 to 70: a wide gap.
Pick gitnexus if you are
Developers giving AI coding agents repo-wide dependency and impact context
- Precomputes clusters and flows at index time, so one tool call returns impact context
- 19 MCP tools including impact, trace, detect_changes, rename and raw Cypher
Pick code-review-graph if you are
Developers who want coding assistants to read fewer files when reviewing changes
- One install command detects and configures about 16 AI coding tools, with a clean uninstall
- Incremental updates re-parse only SHA-256-changed files; two-file edit on django took about 2.5 s
| What we compare | gitnexus | code-review-graph |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 94, widely used | 90, widely used |
| Momentum | Not scored for this kind | Not scored for this kind |
| Freshness | 100, active | 100, active |
| Maintenance | 94, healthy | 93, healthy |
| Agent-ready | 100, ready | 70, partly |
| Facts from GitHub and the README | ||
| Stars | 48.4k | 32.7k |
| License | custom license (read the license) | MIT (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Sep 2026 | Nov 2026 |
| Language | TypeScript | Python |
| Docker | Yes | Yes |
| GPU | Optional | Not needed |
| arm64 or Apple Silicon | Not stated | Not stated |
gitnexus
GitNexus indexes a repository with Tree-sitter into a knowledge graph of dependencies, call chains, clusters and execution flows, stored in LadybugDB. It exposes 19 MCP tools (impact, trace, detect_changes, rename, cypher and others) plus agent skills and hooks for Claude Code, Cursor, Codex and similar editors. A browser Web UI adds graph exploration and chat.
Who it is for: Developers giving AI coding agents repo-wide dependency and impact context
Strengths
- Precomputes clusters and flows at index time, so one tool call returns impact context
- 19 MCP tools including impact, trace, detect_changes, rename and raw Cypher
- One setup command writes MCP config for Claude Code, Cursor, Codex, Antigravity and others
- Installs agent skills and Claude Code and Codex pre/post tool hooks
Weaknesses
- PolyForm Noncommercial license restricts commercial use
- In-browser Web UI mode is limited to roughly 5k files
- npm 11 install crash and native grammar builds complicate installation
- Render deploy costs about $35/month; the access token is the only control
- RAM ≥ 2 GB
- GPU optional
- Docker + Compose
- Needs Node.js, LadybugDB, Tree-sitter
code-review-graph
Parses a repository with Tree-sitter into a SQLite graph of functions, classes, imports, calls and tests, then serves blast-radius and risk-scored context over MCP so the assistant reads only affected files. The installer configures about 16 tools (Claude Code, Cursor, Codex, Windsurf, Zed and others) and updates incrementally via hooks, git hooks or watch mode. A GitHub Action posts risk-scored PR comments.
Who it is for: Developers who want coding assistants to read fewer files when reviewing changes
Strengths
- One install command detects and configures about 16 AI coding tools, with a clean uninstall
- Incremental updates re-parse only SHA-256-changed files; two-file edit on django took about 2.5 s
- Covers 30+ languages plus notebooks, and custom grammars via languages.toml
- Runs locally; the GitHub Action builds the graph on the CI runner without sending code out
Weaknesses
- Impact recall of 1.0 is circular, since ground truth comes from the same graph
- Against a grep baseline, median token reduction is 6.65x, not the 63x headline
- Graph context can cost more tokens than a plain read for small single-file edits
- Cold build of a roughly 3,000-file repository took about 40 seconds
- no GPU
- Docker
- Needs Python 3.10+, Tree-sitter, SQLite
- Models: all-MiniLM-L6-v2 (local embeddings)
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.