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.

LM Studio

Give local models in LM Studio access to your memos.

Needs LM Studio 0.3.17 or later, and 0.4.10 or later to sign in.

Install in one click

Add to LM Studio opens the app and adds GigaRAG with your agent key. Sign in to get your key, then install in one click.

Sign in to install

Or use the GigaRAG CLI

One command connects LM Studio 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 LM Studio afterwards. Nothing here expires, and gigarag connect --remove takes GigaRAG back out of everything it touched.

Sign in with GigaRAG

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

  1. 1.

    Add GigaRAG without a header

    mcp.json
    {
  "mcpServers": {
    "gigarag": { "url": "https://mcp.gigarag.com/mcp" }
  }
}
  2. 2.

    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 set it up by hand

  1. 1.

    Open the Program tab, then Install, then Edit mcp.json

  2. 2.

    Add GigaRAG and save

    mcp.json
    {
  "mcpServers": {
    "gigarag": {
      "url": "https://mcp.gigarag.com/mcp",
      "headers": { "Authorization": "Bearer <api-key>" }
    }
  }
}

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: MCP in LM Studio, Install links