RabbitHoles AI
Infinite-canvas AI chat client that lets you branch, fork, and connect conversations as nodes instead of scrolling a single linear thread.
Pick RabbitHoles AI if you do serious multi-thread research and want to see your reasoning graph instead of scrolling a single chat to oblivion.
Skip it if you want a hosted, collaborative team chat or a managed subscription that bundles model costs for you.
RabbitHoles AI is a desktop chat client built around an infinite canvas where every conversation lives as its own node. Instead of cramming research into one runaway thread, you spawn branches from any message, drag related chats onto the same board, and pull in PDFs, websites, images, and YouTube transcripts as extra context. Conversations are stored locally on your machine, and you bring your own API keys for the underlying providers.
It is built for researchers, developers, and knowledge workers who routinely chase tangents and want to keep the trail visible. The pricing is a one-time lifetime purchase (around $249 retail, frequently discounted to ~$79 on deal sites) on a bring-your-own-key model, which makes it a sharp counter to the $20/mo-per-app subscription pile if you already pay OpenAI, Anthropic, Google, Groq, or Perplexity directly. There is also an MIT-licensed open-source spinoff (AsyncFuncAI/rabbitholes) for the curious.
Under the hood it is multi-model: switch between Anthropic, Google, Groq, Perplexity, and custom providers per node, with per-node system prompt and temperature. Exports to JSON or Markdown, unlimited canvases, and the local-first storage model mean your research graph is portable rather than locked inside someone's cloud.
RabbitHoles nails the right metaphor for how research actually unfolds: not a chat log, a graph. The lifetime + BYO-key pricing is genuinely refreshing, and multi-model routing per node is a power-user feature most chat apps still botch. Just know you are buying a tool, not a model bundle.
— The AI Tool Bible editorial team
Pros
- ✅ Infinite canvas with true branching beats linear chat for deep research
- ✅ Multi-model: Anthropic, Google, Groq, Perplexity, custom providers
- ✅ Local-first storage keeps conversations on your device
- ✅ Lifetime license sidesteps another monthly AI subscription
- ✅ PDF, website, image, and YouTube context drops into any node
Cons
- ⚠️ BYO API keys means usage costs are still on you
- ⚠️ Desktop-only workflow; no real collaborative multiplayer
- ⚠️ Canvas UI has a learning curve vs. plain chat
- ⚠️ Smaller ecosystem than ChatGPT or Claude apps
Use cases
Explore related
Compare with similar tools
All in Agents →LangGraph
FeaturedStateful, graph-based agent orchestration from LangChain.
CrewAI
FeaturedPython framework for multi-agent orchestration.
Claude Agent SDK
Anthropic's official SDK for building autonomous Claude agents.
Manus
Generalist agent for research, code, and web tasks.
Devin
Cognition Labs' "autonomous software engineer" agent.
AutoGPT
Open-source platform for building autonomous AI agents.