private-gpt
zylon-ai/private-gpt
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, and more
Why pick itSupports multiple local models and tools, suitable for enterprise deployment
Install
- GitHub
- zylon-ai/private-gpt
- Website
- zylon.ai
- Stars
- ★ 57.6k
- License
- Apache-2.0
- Language
- Python
- Last push
- Oct 29, 2026
- Category
- Run locally
Good for
- Build private AI apps
- Support RAG and tools
- Enterprise deployment
- Local model integration
Getting started
- Install PrivateGPT
- Start LLM server
- Run PrivateGPT
- Access UI
Before you install
Requires a running OpenAI-compatible LLM server, like Ollama.
Summarized by AI from the project docs; check the official docs before relying on it.
Similar tools
- rtkRun locally · ★ 85k
CLI proxy that reduces LLM token consumption by 60-90%
- unslothRun locally · ★ 78.8k
GUI app to run and train large language models and diffusion models locally
- LocalAIRun locally · ★ 50.1k
Run any AI model on any hardware, no GPU required
- codebase-memory-mcpRun locally · ★ 47.8k
Local code intelligence tool that connects code, docs, and infrastructure in a persistent graph.
- OllamaRun locally · ★ 185k
Download and run open-weight models like Qwen, DeepSeek, Gemma and gpt-oss locally with one command, with an OpenAI-compatible API.
Source GitHub · Updated Oct 28, 2026 · All rights belong to the original creators