Installation
1. Run the installer
Section titled “1. Run the installer”npx @colbymchenry/codegraphThe installer will:
- Ask which agent(s) to configure — auto-detecting installed ones from Claude Code, Cursor, Codex CLI, opencode, Hermes Agent, Gemini CLI, Antigravity IDE, Kiro, GitHub Copilot (VS Code, Copilot CLI, JetBrains IDEs), IBM Bob, Factory Droid, Windsurf, Qwen Code, DeepSeek Harness, Grok Build, Kimi Code, Qoder CLI, and Pi.
- Prompt to install
codegraphon yourPATH(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 (Integrations lists the file for each agent). Claude Code, Codex CLI, Gemini CLI, opencode, Factory Droid, Qwen Code, DeepSeek Harness, Grok Build, Kimi Code and Pi also get a small marker-fenced CodeGraph section in their instructions file (
CLAUDE.md/AGENTS.md/GEMINI.md/QWEN.md, orrules/codegraph.mdfor Grok Build); the others get the MCP config only. Removed cleanly bycodegraph uninstall. - Set up auto-allow permissions when Claude Code or Qwen Code is one of the targets.
The installer wires up your agents only — it does not index your code. After it finishes, build each project’s graph yourself with codegraph init (step 3 below).
Non-interactive (scripting / CI)
Section titled “Non-interactive (scripting / CI)”codegraph install --yes # auto-detect agents, install globalcodegraph install --target=cursor,claude --yes # explicit target listcodegraph install --target=auto --location=local # detected agents, project-localcodegraph 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 the auto-allow list (Claude Code, Qwen Code) | permissions on |
--print-config <id> | dump snippet for one agent and exit | — |
--init | (boolean) after wiring agents, also run codegraph init in the current folder | off |
--refresh | (boolean) rewrite what earlier installs configured, for agents already set up; codegraph upgrade runs it for you | off |
2. Restart your agent
Section titled “2. Restart your agent”Restart your agent (Claude Code / Cursor / Codex CLI / opencode / Hermes Agent / Gemini CLI / Antigravity IDE / Kiro / VS Code, the Copilot CLI, or your JetBrains IDE for GitHub Copilot / IBM Bob / Factory Droid / Windsurf / Qwen Code / DeepSeek Harness / Grok Build / Kimi Code / Qoder CLI / Pi) for the MCP server to load.
3. Initialize projects
Section titled “3. Initialize projects”cd your-projectcodegraph initcodegraph init creates the local .codegraph/ directory and builds the full graph in the same step — one command. A single global codegraph install covers every project; you run codegraph init once per project.
Supported platforms
Section titled “Supported platforms”Every release ships a self-contained build (bundled Node runtime — nothing to compile) for all three desktop OSes, on both x64 and arm64:
| Platform | Architectures | Install |
|---|---|---|
| Windows | x64, arm64 | PowerShell installer or npm |
| macOS | x64, arm64 | shell installer or npm |
| Linux | x64, arm64 | shell installer or npm |
As of CodeGraph 1.6.3 the bundled runtime is Node.js 24.22.1, Node’s October 2026 security release, which fixes CVE-2026-111497. Every release checks the Node.js it bundles against the checksums nodejs.org publishes.
Uninstall
Section titled “Uninstall”Changed your mind? One command removes CodeGraph from every agent it configured and the CLI itself: every install it finds (standalone bundle, npm global package, launcher link), shown to you before anything is deleted. Pass --keep-cli to remove only the agent configurations:
codegraph uninstallThis reverses the installer — stripping 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.