What it does
PrivateGPT is a layer that sits between your own AI model and the apps you build. It doesn't run models itself; it connects to a model server you already run, such as Ollama.
On top of that it adds the pieces most AI apps need: reading your files, answering questions about them with citations, built-in tools like web search, connections to databases, and support for MCP connectors (a standard way to plug tools into AI).
It includes a simple web page for testing and demos, but its makers say the programming interface is the real product. The aim is to build AI apps without sending data to cloud services.
Who it's for
Developers and companies building private, in-house AI tools.
Can I use it without coding?
Developers only. Needs a terminal install plus a separate AI model server; it's meant as a base for building apps. New to this? Start here.
Can I run it?
- Cost
- Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
- Runs on
- Mac, Windows, Linux
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Install and start a local AI model server, such as Ollama.
- Install PrivateGPT for your system and start it, pointing it at that server.
- Open the built-in workbench in your web browser to chat and upload documents.
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 (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe