Overview
PrivateGPT is an open-source API layer that turns local models into production AI applications. It provides higher-level building blocks for building AI applications, following the Claude API model, so developers can build private AI products without rebuilding backend primitives from scratch or depending on cloud APIs. It is described as production-tested, powering Zylon, an on-premise AI platform.
PrivateGPT does not run models itself; it connects to any OpenAI-compatible inference server via OPENAI_API_BASE, and works with any server that implements /v1/chat/completions and /v1/models. It ships a built-in workbench UI for testing and demos at /ui, though the API is described as the actual product.
The API includes a standard messages API with streaming, async, and token counting; file and artifact ingestion; retrieval with citations and agentic RAG; built-in tools mirroring the Claude API such as web search, web fetch, and code execution; custom tools and MCP connectors; structured access to databases and CSVs; and embeddings and orchestration.
PrivateGPT began as a 2023 proof of concept for chatting with documents fully offline, and version 1.0 was rebuilt from the ground up as a proper API layer for private AI applications. It is maintained by the team at Zylon.
Pricing
Free
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Teams use PrivateGPT to run local models as the backend for agentic coding in the terminal.
- Teams use PrivateGPT to connect the Claude desktop app and Cowork to their private models.
- Teams use PrivateGPT to run private AI inside Word, Excel, Outlook, and PowerPoint.
- Teams use PrivateGPT as a local AI coding assistant in the terminal.
- Teams use the workbench UI to test retrieval with citations.
- Teams use the workbench UI to upload documents.
- Teams use the workbench UI to configure databases, MCP connectors, skills, and custom tools.
- Teams use PrivateGPT for structured access to databases and CSVs.
Features
API layer for private AI applications
Local model support
Retrieval augmented generation capabilities
Skills and tools support
Model Context Protocol support
Text to SQL capabilities
OpenAI compatible inference server support
Reviews
No reviews yet. Be the first to share your experience!