* fix: consolidate C/C++/C#/Rust language support from 6 overlapping PRs Merges fixes from PRs #163, #170, #178, #216, #227, #234 into a single coherent changeset with shared modules and deduplication. Phase 0 — Pre-merge consolidation: - Extract isNodeExported to shared export-detection.ts module - Extract TREE_SITTER_BUFFER_SIZE to shared constants.ts with adaptive sizing - Consolidate FUNCTION_NODE_TYPES, extractFunctionName, isBuiltInOrNoise from duplicated call-processor.ts and parse-worker.ts into shared utils.ts - Add query compilation smoke tests for all 12 languages Language fixes: - fix(c/cpp): isExported checks static linkage instead of returning false - fix(c/cpp): .h files parsed as C++ (tree-sitter-cpp is superset of C) - fix(c/cpp): expanded entry point patterns (~30 new for C, ~18 for C++) - fix(cpp): add typedef, union, macro, prototype, inline method queries - fix(c#): isExported scans sibling modifiers instead of parent walk - fix(c#): heritage queries use correct base_list AST structure - fix(c#): add framework detection, import resolution, entry point scoring - fix(rust): isExported scans sibling visibility_modifier in declaration - fix(builtins): remove open/read/write/close (real C POSIX syscalls) - fix(buffer): adaptive bufferSize (2x fileSize, 512KB-32MB range) - feat(ts/js): add call_expression query patterns for const assignments Deduplication: - call-processor.ts: -226 lines (uses shared utils) - parse-worker.ts: -320 lines (uses shared utils) - parsing-processor.ts: -156 lines (uses shared export-detection) * perf: fix review findings — hoist Sets, deduplicate DEFINITION_CAPTURE_KEYS - Hoist CSHARP_DECL_TYPES and RUST_DECL_TYPES to module-level constants in export-detection.ts (was allocating new Set on every isNodeExported call) - Extract DEFINITION_CAPTURE_KEYS and getDefinitionNodeFromCaptures to shared utils.ts (was duplicated in parsing-processor.ts and parse-worker.ts) - Pre-compute merged entry point patterns to avoid per-call array spread in calculateEntryPointScore * test: add C, C++, and Tree-sitter buffer size tests * fix: C/C++/Rust review findings + comprehensive test coverage (+72 tests) Source fixes: - Add Rust built-in noise (unwrap, clone, into, collect, panic, etc.) - C++ anonymous namespace → internal linkage (not exported) - Replace .text regex with storage_class_specifier child scan (perf) - Raise file skip threshold from 512KB to 32MB (TREE_SITTER_MAX_BUFFER) - Export TREE_SITTER_MAX_BUFFER from constants.ts - Add C++ double pointer query patterns to CPP_QUERIES - Add C#: record_struct, record_class, file_scoped_namespace to decl types - Add Rust: union_item to visibility scanning set Tests (214 → 286): - ingestion-utils: +24 (Rust/C# noise, pointer/ref/destructor extraction, buffer) - parsing: +36 (real AST C/C++ static/namespace, Rust/C#/Java/PHP/Swift edge cases) - tree-sitter-languages: +12 (query accuracy for C/C++/C#/Rust captures) |
||
|---|---|---|
| .. | ||
| hooks/claude | ||
| scripts | ||
| skills | ||
| src | ||
| test | ||
| vendor/leiden | ||
| .npmignore | ||
| package-lock.json | ||
| package.json | ||
| README.md | ||
| tsconfig.json | ||
| tsconfig.test.json | ||
| vitest.config.ts | ||
GitNexus
Graph-powered code intelligence for AI agents. Index any codebase into a knowledge graph, then query it via MCP or CLI.
Works with Cursor, Claude Code, Windsurf, Cline, OpenCode, and any MCP-compatible tool.
Why?
AI coding tools don't understand your codebase structure. They edit a function without knowing 47 other functions depend on it. GitNexus fixes this by precomputing every dependency, call chain, and relationship into a queryable graph.
Three commands to give your AI agent full codebase awareness.
Quick Start
# Index your repo (run from repo root)
npx gitnexus analyze
That's it. This indexes the codebase, installs agent skills, registers Claude Code hooks, and creates AGENTS.md / CLAUDE.md context files — all in one command.
To configure MCP for your editor, run npx gitnexus setup once — or set it up manually below.
gitnexus setup auto-detects your editors and writes the correct global MCP config. You only need to run it once.
Editor Support
| Editor | MCP | Skills | Hooks (auto-augment) | Support |
|---|---|---|---|---|
| Claude Code | Yes | Yes | Yes (PreToolUse) | Full |
| Cursor | Yes | Yes | — | MCP + Skills |
| Windsurf | Yes | — | — | MCP |
| OpenCode | Yes | Yes | — | MCP + Skills |
Claude Code gets the deepest integration: MCP tools + agent skills + PreToolUse hooks that automatically enrich grep/glob/bash calls with knowledge graph context.
Community Integrations
| Agent | Install | Source |
|---|---|---|
| pi | pi install npm:pi-gitnexus |
pi-gitnexus |
MCP Setup (manual)
If you prefer to configure manually instead of using gitnexus setup:
Claude Code (full support — MCP + skills + hooks)
claude mcp add gitnexus -- npx -y gitnexus@latest mcp
Cursor / Windsurf
Add to ~/.cursor/mcp.json (global — works for all projects):
{
"mcpServers": {
"gitnexus": {
"command": "npx",
"args": ["-y", "gitnexus@latest", "mcp"]
}
}
}
OpenCode
Add to ~/.config/opencode/config.json:
{
"mcp": {
"gitnexus": {
"command": "npx",
"args": ["-y", "gitnexus@latest", "mcp"]
}
}
}
How It Works
GitNexus builds a complete knowledge graph of your codebase through a multi-phase indexing pipeline:
- Structure — Walks the file tree and maps folder/file relationships
- Parsing — Extracts functions, classes, methods, and interfaces using Tree-sitter ASTs
- Resolution — Resolves imports and function calls across files with language-aware logic
- Clustering — Groups related symbols into functional communities
- Processes — Traces execution flows from entry points through call chains
- Search — Builds hybrid search indexes for fast retrieval
The result is a KuzuDB graph database stored locally in .gitnexus/ with full-text search and semantic embeddings.
MCP Tools
Your AI agent gets these tools automatically:
| Tool | What It Does | repo Param |
|---|---|---|
list_repos |
Discover all indexed repositories | — |
query |
Process-grouped hybrid search (BM25 + semantic + RRF) | Optional |
context |
360-degree symbol view — categorized refs, process participation | Optional |
impact |
Blast radius analysis with depth grouping and confidence | Optional |
detect_changes |
Git-diff impact — maps changed lines to affected processes | Optional |
rename |
Multi-file coordinated rename with graph + text search | Optional |
cypher |
Raw Cypher graph queries | Optional |
With one indexed repo, the
repoparam is optional. With multiple, specify which:query({query: "auth", repo: "my-app"}).
MCP Resources
| Resource | Purpose |
|---|---|
gitnexus://repos |
List all indexed repositories (read first) |
gitnexus://repo/{name}/context |
Codebase stats, staleness check, and available tools |
gitnexus://repo/{name}/clusters |
All functional clusters with cohesion scores |
gitnexus://repo/{name}/cluster/{name} |
Cluster members and details |
gitnexus://repo/{name}/processes |
All execution flows |
gitnexus://repo/{name}/process/{name} |
Full process trace with steps |
gitnexus://repo/{name}/schema |
Graph schema for Cypher queries |
MCP Prompts
| Prompt | What It Does |
|---|---|
detect_impact |
Pre-commit change analysis — scope, affected processes, risk level |
generate_map |
Architecture documentation from the knowledge graph with mermaid diagrams |
CLI Commands
gitnexus setup # Configure MCP for your editors (one-time)
gitnexus analyze [path] # Index a repository (or update stale index)
gitnexus analyze --force # Force full re-index
gitnexus analyze --embeddings # Enable embedding generation (slower, better search)
gitnexus analyze --verbose # Log skipped files when parsers are unavailable
gitnexus mcp # Start MCP server (stdio) — serves all indexed repos
gitnexus serve # Start local HTTP server (multi-repo) for web UI
gitnexus list # List all indexed repositories
gitnexus status # Show index status for current repo
gitnexus clean # Delete index for current repo
gitnexus clean --all --force # Delete all indexes
gitnexus wiki [path] # Generate LLM-powered docs from knowledge graph
gitnexus wiki --model <model> # Wiki with custom LLM model (default: gpt-4o-mini)
Multi-Repo Support
GitNexus supports indexing multiple repositories. Each gitnexus analyze registers the repo in a global registry (~/.gitnexus/registry.json). The MCP server serves all indexed repos automatically.
Supported Languages
TypeScript, JavaScript, Python, Java, C, C++, C#, Go, Rust, PHP, Swift
Agent Skills
GitNexus ships with skill files that teach AI agents how to use the tools effectively:
- Exploring — Navigate unfamiliar code using the knowledge graph
- Debugging — Trace bugs through call chains
- Impact Analysis — Analyze blast radius before changes
- Refactoring — Plan safe refactors using dependency mapping
Installed automatically by both gitnexus analyze (per-repo) and gitnexus setup (global).
Requirements
- Node.js >= 18
- Git repository (uses git for commit tracking)
Privacy
- All processing happens locally on your machine
- No code is sent to any server
- Index stored in
.gitnexus/inside your repo (gitignored) - Global registry at
~/.gitnexus/stores only paths and metadata
Web UI
GitNexus also has a browser-based UI at gitnexus.vercel.app — 100% client-side, your code never leaves the browser.
Local Backend Mode: Run gitnexus serve and open the web UI locally — it auto-detects the server and shows all your indexed repos, with full AI chat support. No need to re-upload or re-index. The agent's tools (Cypher queries, search, code navigation) route through the backend HTTP API automatically.
License
Free for non-commercial use. Contact for commercial licensing.