Getting started

Welcome to Engrym. This page walks you through installing the CLI, connecting it to a project, and asking your first question of the Brain, in about five minutes.

You'll need Node.js 18 or later.

1. Install the CLI

Engrym ships as an npm package:

npm install -g @engrym/cli

Verify the install:

engrym --version

2. Create a project in the dashboard

Sign up at dashboard.engrym.com and create a project. The onboarding flow generates a setup token (a per-project credential) and shows you a one-line connect command.

3. Connect your machine

Run the one-liner from the dashboard. It authenticates the CLI and registers the Engrym MCP server with your AI tool in a single step:

ENGRYM_SETUP_TOKEN=<your-token> npx @engrym/cli setup claude-code

Supported tools: claude-code, claude-desktop, cursor, windsurf, gemini, codex. The project is resolved automatically from the token. The token is stored once, in ~/.engrym/config.yaml (file mode 600), and it is never written into any tool's config.

Prefer a hosted connector with no local install, or connecting on ChatGPT, the web, or iOS where npx can't run? Use the remote OAuth connector at https://engrym-mcp-remote.fly.dev/mcp instead; you authorize once in the browser.

Check the connection:

engrym status

See MCP setup for per-tool details and the remote connector walkthrough.

4. Bring in your existing docs

If your project knowledge already lives in Markdown, import it. The Brain extractor unpacks knowledge atoms (conventions, constraints, decisions, context) in the background, using your own provider key (BYOK), configured in the dashboard.

engrym import obsidian-vault ~/vaults/my-project
engrym import markdown-folder ./docs

Both commands print an import id; track progress with:

engrym import status <importId>

You can also create documents directly:

engrym doc create docs/architecture/providers.md --content "# Provider strategy"

5. Query the Brain

Ask your AI agent (Claude Code, Cursor, Windsurf, Gemini CLI, Codex, ChatGPT) a question about your project. With the MCP server wired in step 3, the agent surfaces the relevant atoms automatically. Or query directly from the terminal:

engrym brain query "provider strategy"

brain query is full-text search across atoms; it needs the project connection from step 3. For the composed context bundle an agent sees, try:

engrym brain context

Next steps