ArchestackGitHub ↗ (opens in a new tab)

#77th of 15 in RAG and knowledge

PrivateGPT

Anthropic-style API layer for private RAG on local inference servers

Documentation ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)
Stars
57.6k
License
Apache-2.0
Last commit
Oct 2026
Last release
Jun 2026

Overview

PrivateGPT 1.0 is an API server shaped like the Anthropic Messages API, adding file ingestion, retrieval with citations, web search, code execution, MCP and direct database or CSV querying. It runs no models; it calls any OpenAI-compatible server (Ollama, llama.cpp, vLLM) through OPENAI_API_BASE. A workbench UI at /ui on port 8080 exists for testing; the API is the product.

Who it is for: developers building private AI apps on local models

Strengths

  • Anthropic Messages API shape, so Claude Code, Claude Desktop and Office add-ins can target it
  • Backend-agnostic: any OpenAI-compatible inference server via OPENAI_API_BASE
  • Built-in database and CSV querying, no extra tool server needed
  • Installs with brew or uv tool install; Docker also documented

Weaknesses

  • Runs no models; a separate inference server and embedding server are required
  • No prompt caching and no OAuth or organizations
  • Skills support is marked basic; structured output depends on the backend
  • RBAC, LDAP, connectors and audit logs exist only in the commercial Zylon platform

What it needs

  • no GPU
  • Docker
  • Needs OpenAI-compatible inference server (Ollama, llama.cpp, vLLM)
  • Models: any model behind an OpenAI-compatible /v1/chat/completions endpoint
  • port 8080

Also in RAG and knowledge

See all 15
Also in RAG and knowledge
RankProjectScore
1LightRAGGraph-plus-vector RAG server with web UI and Ollama-compatible API40.1k stars, MIT76 out of 100
2Open NotebookSelf-hosted NotebookLM alternative with podcasts and 20+ model providers40k stars, MIT75 out of 100
3RAGFlowRAG engine with document parsing, agentic retrieval and citations Live demo ↗ (opens in a new tab)92k stars, Apache-2.072 out of 100
#4WeKnoraEnterprise knowledge base combining RAG Q&A, agents and generated wikis33k stars, custom license68 out of 100
#5SurfSenseOffline NotebookLM alternative that turns documents into decks, reports and podcasts16.3k stars, custom license68 out of 100