Rabbithole

Rabbithole

**An infinite canvas for learning.** Open a document, select any text, ask a question — and the answer opens as a fully-rendered child document. Follow whatever pulls at you, as deep as it goes. Every hole is saved and revisitable.

🌐 **[rabbithole.ing](https://rabbithole.ing)**

There are two ways in:

• The web app — rabbithole.ing. Use the Claude or ChatGPT plan you already pay for (npx @shlokkhemani/rabbithole bridge), bring an OpenRouter key, run a local model, or point it at your own endpoint. Static site, no account, no backend: your key stays in your browser, and so do your documents.
• The MCP server — for terminal agents. Claude Code, Codex, or any MCP client does the answering; Rabbithole gives it a canvas in your browser. The server, storage, and canvas all run on your machine — your documents and questions go only to the agent you already use.

Use it on the web

Open **[rabbithole.ing](https://rabbithole.ing)** and start from anywhere: drop in a PDF or Markdown file, paste a URL, import a `.rabbithole` or snapshot `.html` — or just ask a question and let the answer become your first document.

Four ways to run a model:

• **Claude & ChatGPT plans** — already pay for Claude or ChatGPT? One command:

  npx @shlokkhemani/rabbithole bridge

  It prints a link; clicking it connects the page. Answers come from the Claude Code or Codex CLI on your machine — your plan, your machine, no extra key. (Needs `claude` or `codex` installed and signed in.)

• **OpenRouter** — one key, every major model. The model picker pulls OpenRouter's live catalog.

• **Local** — Ollama on your machine, with setup help and installed-model discovery. No key required.

• **Custom** — any other OpenAI-compatible endpoint: LM Studio, llama.cpp, vLLM, LiteLLM, or a hosted API. Paste the base URL, add a key if it needs one, and Rabbithole lists the models it offers. The endpoint has to allow b