What it does
Local Deep Research is an AI assistant for in-depth research. You ask a question, and it searches many sources, reads what it finds, and writes up an answer with proper citations.
It can search the general web, research libraries like arXiv and PubMed, and your own private documents. You can also build your own searchable knowledge base. It works with local AI models through tools like Ollama, or with cloud AI services.
Its makers say everything can run on your own computer, with data stored encrypted. They also report strong results on question-answering tests using a model running on a single home graphics card.
Who it's for
Students, researchers, journalists and curious people who want thorough, sourced answers while keeping their data private.
Can I use it without coding?
With some setup. It is set up with Docker or Python, then used through a web page on your computer. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac, Windows, Linux
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Not needed
Try it
- Install Docker on your computer.
- Download the project's Docker Compose file and start it as the README shows.
- After about 30 seconds, open its web page on your computer and ask a research question.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- Local Deep Research – ArXiv, wiki and other searches includedHacker News · Mar 2025