gitnexus vs codebase-memory-mcp
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
codebase-memory-mcp
Local MCP server that indexes code into a queryable knowledge graph
Verdict
gitnexus ranks higher, 89 to 69. Of the 5 score parts we measure for both, gitnexus leads on 4, codebase-memory-mcp on none and 1 is even.
- Adoptiongitnexus leads by 4 points, 77 to 73: close to even.
- FreshnessEven at 100.
- Maintenancegitnexus leads by 11 points, 92 to 81.
- Easy to rungitnexus leads by 33 points, 83 to 50: a wide gap.
- Agent-readygitnexus leads by 100 points, 100 to 0: 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 codebase-memory-mcp if you are
Developers using coding agents on large or unfamiliar codebases
- Single native binary for macOS, Linux and Windows; no Docker, runtime or API key needed
- 162 tree-sitter grammars compiled in; hybrid LSP type resolution for 13 languages
| What we compare | gitnexus | codebase-memory-mcp |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 77, popular | 73, popular |
| Freshness | 100, active | 100, active |
| Maintenance | 92, healthy | 81, healthy |
| Easy to run | 83, very easy | 50, easy |
| Agent-ready | 100, ready | 0, none |
| Facts from GitHub and the README | ||
| Stars | 47.9k | 46.6k |
| License | custom license (read the license) | MIT (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Sep 2026 | Sep 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
codebase-memory-mcp
A native C MCP server that indexes functions, classes, imports and HTTP routes across 162 languages into a local graph, and exposes 17 tools (search, trace, impact analysis, Cypher queries, dead code detection) to coding agents such as Claude Code and Codex. Indexing and queries need no hosted service or API key. A browser UI, CBM Lens Beta, adds source reading, architecture maps and optional local chat, but it is only on main, not in v0.11.0.
Who it is for: Developers using coding agents on large or unfamiliar codebases
Strengths
- Single native binary for macOS, Linux and Windows; no Docker, runtime or API key needed
- 162 tree-sitter grammars compiled in; hybrid LSP type resolution for 13 languages
- Reports Linux kernel (28M LOC) indexed in about 3 minutes
- Installer configures 45 detected agent client surfaces automatically
Weaknesses
- CBM Lens Beta is only on main; the current release ships the older graph UI
- Token savings (120x, 10x) come from the project's own benchmarks
- Preprint reports lower answer quality than file-by-file exploration (83% vs 92%)
- Installer rewrites agent configs and a shared daemon requires identical builds across sessions
- no GPU
- Needs Hugging Face (optional model download for Lens chat)
- port 9749
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.