Back to GigaRAG

Connect an agent

Give an AI tool access to your GigaRAG Workspace, so it can search, read and write your memos while it works.

Gemini CLI

Google's open source terminal agent.

Connect with the GigaRAG CLI

One command connects Gemini CLI and every other AI tool on this machine. Signing in happens in your browser, so no key is written into any config file.

npm install -g gigarag
gigarag login
gigarag connect

Restart Gemini CLI afterwards. Nothing here expires, and gigarag connect --remove takes GigaRAG back out of everything it touched.

Sign in with GigaRAG

Connect without a key: Gemini CLI opens your browser, you sign in to GigaRAG and pick this workspace.

  1. 1.

    Add GigaRAG without a key

    gemini mcp add --transport http --scope user gigarag https://mcp.gigarag.com/mcp
  2. 2.

    Start the sign-in from a Gemini CLI session

    /mcp auth gigarag
  3. 3.

    Sign in with your GigaRAG account

    Your browser opens GigaRAG. Pick the workspace to share and approve. No key is stored in the app, and the connection does not expire.

Or paste a prompt

Paste this into Gemini CLI. It carries your agent key and tells the agent exactly what to change, so it sets the connection up itself.

Run this to add GigaRAG:
gemini mcp add --transport http --scope user gigarag https://mcp.gigarag.com/mcp -H "Authorization: Bearer <api-key>"

Remove any existing gigarag first. Then tell me to restart Gemini CLI. Don't repeat the key.

Or set it up by hand

  1. 1.

    Run this in a terminal

    Without --scope user it is added to the current project only.

    gemini mcp add --transport http --scope user gigarag https://mcp.gigarag.com/mcp -H "Authorization: Bearer <api-key>"
  2. 2.

    Restart Gemini CLI

    Run /mcp in a session to see gigarag listed.

Check it worked

Send this once it is connected. An answer drawn from your workspace means the connection is live.

List my GigaRAG buckets.

Written from the official docs: Gemini CLI MCP