HomeProjectsArticlesPK BoardAbout
Explore Projects

Private GPT

Active
GitHub Python Apache-2.0

Description

PrivateGPT is a fully-local AI application API layer with RAG, agents and multi-model routing, providing zero-data-leak private deployment.

Key Features

  • Fully local — independent of external APIs, all data stays on-prem
  • RAG first-class — built-in ingestion, retrieval and context assembly
  • Multi-model routing — llama.cpp, Ollama, vLLM and other local inference backends
  • Agent SDK — tool calling, planning and multi-step execution abstractions
  • OpenAI-compatible API — /v1 endpoints compatible with OpenAI clients
  • Observability — built-in logging and production-grade observability hooks

Use Cases

💡 Building compliant on-prem RAG and agent services
💡 Exposing an OpenAI-compatible API inside an enterprise
💡 Unified abstraction across multiple local model providers
💡 Connecting private document stores to agents without external calls

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (57.4k stars)
  • • Permissive open-source license (Apache-2.0)
  • • Established track record (3 years in production)

Tags

rag private-ai llm self-hosted api

Categories

📚 RAG Tools ⚡ Agent Tools

Quick Start

git clone https://github.com/zylon-ai/private-gpt
cd private-gpt
poetry install --with ui
make run
Visit GitHub Visit Website

Related Projects

WrenAI

17.3k · Python
Active A

Open-source text-to-SQL and text-to-chart GenBI agent with a semantic layer. Ask your database questions in natural language and get accurate SQL, charts, and BI insights. Supports 12+ data sources and any LLM.

llmtypescriptagent +2
  • · Open context layer providing business semantics, examples, and governance for AI agents
  • · Agent-driven design with CLI-embedded workflow guides loaded on demand
  • · Modeling Definition Language (MDL) for models, relationships, cubes, metrics, and RLAC/CLAC
View full details → View on GitHub

PromptTools

3.0k · Python
Stale B

PromptTools provides open-source tools for prompt testing and experimentation, supporting multiple LLMs (OpenAI, LLaMA) and vector databases (Chroma, Weaviate, LanceDB) to help developers systematically evaluate and optimize RAG systems.

prompt-testingragevaluation +3
  • · Open-source prompt testing and experimentation across multiple LLM providers
  • · Supports OpenAI, Anthropic, LLaMA, Mistral, Gemini, HuggingFace, and more
  • · Vector database evaluation: Chroma, Weaviate, Qdrant, LanceDB, Pinecone
View on GitHub

AI Engineering Hub

37.0k · Jupyter Notebook
Active A+

In-depth tutorials on LLMs, RAGs and real-world AI agent applications. Rich notebook examples for learning AI engineering practices.

ragagentllm +1
  • · 93+ production-ready projects — Covering OCR, RAG, agents, voice, multimodal, and more
  • · Three difficulty tiers — Beginner (22), intermediate (48), advanced (23) projects for progressive learning
  • · LLM hands-on tutorials — Local deployment and applications with DeepSeek, Llama, Gemma, Qwen models
View full details → View on GitHub