CodeGraph Branch

CodeGraph

Supercharge Claude Code, Cursor, Codex, OpenCode, Hermes Agent, Gemini, Antigravity, and Kiro with Semantic Code Intelligence

~35% cheaper · ~70% fewer tool calls · 100% local

Documentation & Website →

[](https://www.npmjs.com/package/@colbymchenry/codegraph) [](https://opensource.org/licenses/MIT) [](https://nodejs.org/)

[](#supported-platforms) [](#supported-platforms) [](#supported-platforms)

[](#supported-agents) [](#supported-agents) [](#supported-agents) [](#supported-agents) [](#supported-agents) [](#supported-agents) [](#supported-agents) [](#supported-agents)

[English](README.md) | [中文](README.zh-CN.md)

Get Started

No Node.js required — one command grabs the right build for your OS:

# macOS / Linux
curl -fsSL https://raw.githubusercontent.com/colbymchenry/codegraph/main/install.sh | sh

# Windows (PowerShell)
irm https://raw.githubusercontent.com/colbymchenry/codegraph/main/install.ps1 | iex

Already have Node? Use npm instead (works on any version):

npx @colbymchenry/codegraph        # zero-install, or:
npm i -g @colbymchenry/codegraph

CodeGraph bundles its own runtime — nothing to compile, no native build, works the same everywhere. The interactive installer auto-configures your agent(s) — Claude Code, Cursor, Codex CLI, opencode, Hermes Agent, Gemini CLI, Antigravity IDE, Kiro.

Initialize Projects

cd your-project
codegraph init -i

Uninstall

Changed your mind? One command removes CodeGraph from every agent it configured:

codegraph uninstall

Reverses the installer — strips CodeGraph's MCP server config, instructions, and permissions from each configured agent. Your project indexes (.codegraph/) are left untouched; remove those per-project with codegraph uninit. Use --target to remove from specific agents, or --yes to run non-interactively.

---

Why CodeGraph?

When Claude Code explores a codebase, it spawns Explore agents that scan files with grep, glob, and Read — consuming tokens on every tool call.

CodeGraph gives those agents a pre-indexed knowledge graph — symbol relationships, call graphs, and code structure. Agents query the graph instantly instead of scanning files.

Benchmark Results

Tested across 7 real-world open-source codebases spanning 7 languages, comparing an agent (Claude Code, headless) answering one architecture question with and without CodeGraph. Each cell is the savings at the median of 4 runs per arm. Re-validated on v0.9.4 (2026-05-24).

> Average: 35% cheaper · 57% fewer tokens · 46% faster · 71% fewer tool calls

| Codebase | Language | Cost | Tokens | Time | Tool calls | |----------|----------|------|--------|------|------------| | VS Code | TypeScript · ~10k files | 26% cheaper | 78% fewer | 52% faster | 85% fewer | | Excalidraw | TypeScript · ~640 | 52% cheaper | 90% fewer | 73% faster | 96% fewer | | Django | Python · ~3k | 12% cheaper | 36% fewer | 19% faster | 53% fewer | | Tokio | Rust · ~790 | 82% cheaper | 86% fewer | 71% faster | 92% fewer | | OkHttp | Java · ~645 | 2% cheaper | 13% fewer | 31% faster | 45% fewer | | Gin | Go · ~110 | 21% cheaper | 34% fewer | 27% faster | 40% fewer | | Alamofire | Swift · ~110 | 47% cheaper | 64% fewer | 48% faster | 83% fewer |

The gains scale with codebase size: on large repos the agent answers from the index in a handful of calls with zero file reads, while the no-CodeGraph agent fans out across grep/find/Read (and the sub-agents it spawns). On a small repo like Gin (~150 files) native search is already cheap, so the margin narrows.

Full benchmark details

Methodology. Each arm is claude -p (Claude Opus 4.7) run headlessly against the repo with --strict-mcp-config: WITH = CodeGraph's MCP server enabled, WITHOUT = an empty MCP config. Built-in Read/Grep/Bash stay available to both. Same question per repo, 4 runs per arm, median reported. Cost = the run's total_cost_usd; Tokens = total tokens processed (input incl. cached + output); Time = wall-clock; Tool calls = every tool invocation, including those inside any sub-agents the model spawns. Repos cloned at --depth 1 and indexed by the same CodeGraph build that served them. Re-validated on codegraph v0.9.4 (2026-05-24); per-repo numbers move run-to-run with how hard the without-arm thrashes (the median-of-4 smooths it, but tails remain — e.g. Tokio's without-arm hit $2.41/3m one batch).

Queries: | Codebase | Query | |----------|-------| | VS Code | "How does the extension host communicate with the main process?" | | Excalidraw | "How does Excalidraw render and update canvas elements?" | | Django | "How does Django's ORM build and execute a query from a QuerySet?" | | Tokio | "How does tokio schedule and run async tasks on its runtime?" | | OkHttp | "How does OkHttp process a request through its interceptor chain?" | | Gin | "How does gin route requests through its middleware chain?" | | Alamofire | "How does Alamofire build, send, and validate a request?" |

Raw medians — WITH → WITHOUT: | Codebase | Cost | Tokens | Time | Tool calls | |----------|------|--------|------|------------| | VS Code | $0.60 → $0.80 | 601k → 2.8M | 1m 10s → 2m 26s | 8 → 55 | | Excalidraw | $0.43 → $0.90 | 344k → 3.5M | 48s → 2m 58s | 3 → 79 | | Django | $0.59 → $0.67 | 739k → 1.2M | 1m 19s → 1m 38s | 9 → 19 | | Tokio | $0.42 → $2.41 | 379k → 2.6M | 53s → 3m 2s | 4 → 53 | | OkHttp | $0.47 → $0.47 | 636k → 730k | 42s → 1m 1s | 6 → 11 | | Gin | $0.37 → $0.47 | 444k → 675k | 44s → 1m 0s | 6 → 10 | | Alamofire | $0.61 → $1.14 | 1.0M → 2.8M | 1m 17s → 2m 27s | 12 → 69 |

Why CodeGraph wins: with the index available, the agent answers directly — codegraph_context to map the area, then one codegraph_explore for the relevant source — and stops, usually with zero file reads. Without it, the agent (and the Explore sub-agents it spawns) spends most of its budget on discovery (find/ls/grep) before reading the right code. CodeGraph only helps when queried directly, so its instructions steer agents to answer directly rather than delegate exploration to file-reading sub-agents — otherwise a sub-agent reads files regardless and CodeGraph becomes overhead.

---

Key Features

| | | |---|---| | Smart Context Building | One tool call returns entry points, related symbols, and code snippets — no expensive exploration agents | | Full-Text Search | Find code by name instantly across your entire codebase, powered by FTS5 | | Impact Analysis | Trace callers, callees, and the full impact radius of any symbol before making changes | | Always Fresh | File watcher uses native OS events (FSEvents/inotify/ReadDirectoryChangesW) with debounced auto-sync — the graph stays current as you code, zero config | | 20+ Languages | TypeScript, JavaScript, Python, Go, Rust, Java, C#, PHP, Ruby, C, C++, Objective-C, Swift, Kotlin, Dart, Lua, Luau, Svelte, Liquid, Pascal/Delphi | | Framework-aware Routes | Recognizes web-framework routing files and links URL patterns to their handlers across 14 frameworks | | Mixed iOS / React Native / Expo | Closes cross-language flows that static parsing misses: Swift ↔ ObjC bridging, React Native legacy bridge + TurboModules + Fabric view components, native → JS event emitters, Expo Modules | | 100% Local | No data leaves your machine. No API keys. No external services. SQLite database only |

How auto-syncing works — and why you don't need to run codegraph sync manually

When your agent (Claude Code, Cursor, Codex, opencode) launches codegraph serve --mcp, three layers keep the index in step with your code — and make sure the agent never gets a silent wrong answer in the brief window between an edit and the next sync:

1. File watcher with debounced auto-sync. A native FSEvents / inotify / ReadDirectoryChangesW watcher captures every source-file create / modify / delete and triggers a re-index after a debounce window (default 2000ms, tunable via CODEGRAPH_WATCH_DEBOUNCE_MS, clamped to [100ms, 60s]). Bursts of edits collapse into a single sync.

1. Per-file staleness banner. During the brief debounce window, MCP tool responses that would reference a still-pending file prepend a ⚠️ banner naming it and telling the agent to Read it directly. Pending files NOT referenced by the response surface as a small footer instead. Either way, the agent gets an explicit signal — validated with Claude Code, where the agent literally says "Reading the file directly for the live content" before opening it.

1. Connect-time catch-up. When the MCP server (re)connects, codegraph runs a fast (size, mtime) + content-hash reconciliation against the working tree before answering the first query — so edits made while no MCP server was running (a git pull from the terminal, edits from another editor, a previous agent session that exited) get absorbed on the next session's first tool call.

agent writes src/Widget.ts
  → watcher fires (

---

## Framework-aware Routes

CodeGraph detects web-framework routing files and emits `route` nodes linked by `references` edges to their handler classes or functions. Querying callers of a view/controller now surfaces the URL pattern that binds it.

| Framework | Shapes recognized |
|---|---|
| **Django** | `path()`, `re_path()`, `url()`, `include()` in `urls.py` (CBV `.as_view()`, dotted paths) |
| **Flask** | `@app.route('/path', methods=[...])`, blueprint routes |
| **FastAPI** | `@app.get(...)`, `@router.post(...)`, all standard methods |
| **Express** | `app.get(...)`, `router.post(...)` with middleware chains |
| **NestJS** | `@Controller` + `@Get/@Post/...`, GraphQL `@Resolver` + `@Query/@Mutation`, `@MessagePattern`/`@EventPattern`, `@SubscribeMessage` |
| **Laravel** | `Route::get()`, `Route::resource()`, `Controller@action`, tuple syntax |
| **Drupal** | `*.routing.yml` routes (`_controller`, `_form`, entity handlers); `hook_*` implementations in `.module`/`.theme`/`.install`/`.inc` |
| **Rails** | `get '/x', to: 'users#index'`, hash-rocket `=>` syntax |
| **Spring** | `@GetMapping`, `@PostMapping`, `@RequestMapping` on methods |
| **Gin / chi / gorilla / mux** | `r.GET(...)`, `router.HandleFunc(...)` |
| **Axum / actix / Rocket** | `.route("/x", get(handler))` |
| **ASP.NET** | `[HttpGet("/x")]` attributes on action methods |
| **Vapor** | `app.get("x", use: handler)` |
| **React Router** / **SvelteKit** | Route component nodes |

---

## Mixed iOS / React Native / Expo bridging

Real iOS and React Native codebases live across multiple languages — a Swift caller invokes an Objective-C selector that's been auto-bridged, a JS file calls into a native module via the React Native bridge, a JSX component delegates to a native view manager. Static tree-sitter extraction stops at each language boundary. CodeGraph bridges them so `trace`, `callers`, `callees`, and `impact` connect end-to-end across the gap.

| Boundary | JS / Swift side | Native side | How |
|---|---|---|---|
| **Swift → ObjC** | Swift `obj.foo(bar:)` | ObjC selector `-fooWithBar:` | `@objc` auto-bridging rules (including init/property/protocol forms) + Cocoa preposition prefixes (`With`/`For`/`By`/`In`/`On`/`At`/…) |
| **ObjC → Swift** | ObjC `[obj fooWithBar:]` | Swift `@objc func foo(bar:)` | Reverse-bridge name candidates; verifies `@objc` exposure from source |
| **React Native legacy bridge** | JS `NativeModules.X.fn(...)` | ObjC `RCT_EXPORT_METHOD` / `RCT_REMAP_METHOD` · Java/Kotlin `@ReactMethod` | Parses macro/annotation declarations to build a JS-name → native-method map |
| **React Native TurboModules** | JS `import M from './NativeM'; M.fn(...)` | Native impl matching the Codegen spec | Treats the `Native.ts` spec interface as ground truth |
| **RN native → JS events** | JS `new NativeEventEmitter(...).addListener('e', cb)` | ObjC `[self sendEventWithName:@"e" body:...]` · Swift `sendEvent(withName: "e", ...)` · Java/Kotlin `.emit("e", ...)` | Synthesized cross-language event channel keyed by literal event name |
| **Expo Modules** | JS `requireNativeModule('X').fn(...)` | Swift / Kotlin `Module { Name("X"); AsyncFunction("fn") { ... } }` | Parses the Expo DSL literals; synthetic method nodes resolve via existing name-match |
| **Fabric view components** | JSX `` | TS Codegen spec + native impl class | Spec → `component` node; convention-based name+suffix lookup (`View`/`ComponentView`/`Manager`/`ViewManager`) bridges to native |
| **Legacy Paper view managers** | JSX `` | ObjC `RCT_EXPORT_VIEW_PROPERTY` · Java/Kotlin `@ReactProp` | Same as Fabric — Paper-era declarations also produce `component` + `property` nodes |

**Validated on real codebases** (small + medium + large for each bridge):

| Bridge | Small | Medium | Large |
|---|---|---|---|
| Swift ↔ ObjC | [Charts](https://github.com/danielgindi/Charts) | [realm-swift](https://github.com/realm/realm-swift) | [Wikipedia-iOS](https://github.com/wikimedia/wikipedia-ios) |
| RN legacy bridge | [AsyncStorage](https://github.com/react-native-async-storage/async-storage) | [react-native-svg](https://github.com/software-mansion/react-native-svg) | [react-native-firebase](https://github.com/invertase/react-native-firebase) |
| RN native → JS events | [RNGeolocation](https://github.com/Agontuk/react-native-geolocation-service) | — | react-native-firebase |
| Expo Modules | expo-haptics | expo-camera | expo SDK sweep (7 packages) |
| Fabric / Paper views | [react-native-segmented-control](https://github.com/react-native-segmented-control/segmented-control) | [react-native-screens](https://github.com/software-mansion/react-native-screens) | [react-native-skia](https://github.com/Shopify/react-native-skia) |

Each bridge emits edges tagged `provenance:'heuristic'` with `metadata.synthesizedBy:` set to a stable channel name (e.g. `swift-objc-bridge`, `rn-event-channel`, `fabric-native-impl`, `expo-module-extract`), so the agent can tell at a glance how a hop got into the graph.

---

## Quick Start

### 1. Run the Installer

```bash
npx @colbymchenry/codegraph

The installer will:

• Ask which agent(s) to configure — auto-detects installed ones from: Claude Code, Cursor, Codex CLI, opencode, Hermes Agent, Gemini CLI, Antigravity IDE, Kiro
• Prompt to install codegraph on your PATH (so agents can launch the MCP server)
• Ask whether configs apply to all your projects or just this one
• Write each chosen agent's MCP server config (the codegraph usage guide is delivered by the MCP server itself, so no instructions file is added to CLAUDE.md / AGENTS.md / etc.)
• Set up auto-allow permissions when Claude Code is one of the targets
• Initialize your current project (local installs only)

Non-interactive (scripting / CI):

codegraph install --yes                              # auto-detect agents, install global
codegraph install --target=cursor,claude --yes       # explicit target list
codegraph install --target=auto --location=local     # detected agents, project-local
codegraph install --print-config codex               # print snippet, no file writes

| Flag | Values | Default | |---|---|---| | --target | auto, all, none, or csv (claude,cursor,...) | prompt | | --location | global, local | prompt | | --yes | (boolean) | prompt every step | | --no-permissions | (boolean) skip Claude auto-allow list | permissions on | | --print-config | dump snippet for one agent and exit | — |

2. Restart Your Agent

Restart your agent (Claude Code / Cursor / Codex CLI / opencode / Hermes Agent / Gemini CLI / Antigravity IDE / Kiro) for the MCP server to load.

3. Initialize Projects

cd your-project
codegraph init -i

Builds the per-project knowledge graph index. A single global codegraph install works in every project you open — no ne

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: lagrahhn
• Source: lagrahhn/codeGraph-branch
• License: MIT

Install and usage instructions live in the source repository linked above.