# Rabbithole

> An infinite canvas for learning. Humans open the browser app at
> `https://rabbithole.ing/` and bring their own model key. Agents install the
> local MCP server and open a local browser canvas for the human.

Source: https://github.com/shlokkhemani/rabbithole
MCP path requires: Node >= 18 and a browser.

## Paths

- Human path: open `https://rabbithole.ing/`. OpenRouter is recommended, with
  Anthropic, OpenAI, and local OpenAI-compatible endpoints also supported. Keys
  stay in the browser except for requests to the provider origin the human
  configures. Holes persist in IndexedDB and can be exported/imported as
  `.rabbithole` files.
- Agent path: install the MCP server below. The agent does the answering and
  Rabbithole opens a local browser canvas.

## Setup

- Claude Code: `claude mcp add rabbithole -- npx -y github:shlokkhemani/rabbithole`
- Codex: `codex mcp add rabbithole -- npx -y github:shlokkhemani/rabbithole`
- Any other MCP client: add the same `npx -y github:shlokkhemani/rabbithole`
  command to its MCP server config.

## Links

- App: https://rabbithole.ing/
- GitHub repo: https://github.com/shlokkhemani/rabbithole
