Best self-hosted Generative Artificial Intelligence (GenAI) apps

Ollama

★ 175,830

Ollama runs large language models (LLMs) like Llama, Mistral and Gemma locally, on your own hardware, with a single command. It's the foundation for private AI at home: nothing goes to the cloud, no per-token cost, and it works offline.

Open-WebUI

★ 144,873

Open WebUI is a ChatGPT-like chat interface for LLMs that connects to Ollama or any OpenAI-compatible API. Hosted by you, it becomes a private ChatGPT for your family or team, with history and users under your control.

LobeHub

★ 79,678

LobeChat (LobeHub) is a modern AI chat interface supporting multiple models, plugins and custom assistants. Hosted by you, it offers a ChatGPT-like experience with your own providers and full conversation privacy.

AnythingLLM

★ 63,011

AnythingLLM is a full AI application that chats with your documents (RAG), with agents and multiple models. Self-hosted, it becomes a private AI knowledge base for you or your team.

LocalAI

★ 47,447

LocalAI runs AI models (text, image, audio) locally, with an API compatible with OpenAI's. Self-hosted, it's a drop-in replacement to run AI without sending data to the cloud or paying per token.

LibreChat

★ 40,506

LibreChat is a ChatGPT-style chat interface that connects multiple AI providers, with multi-user, search and plugins. Self-hosted, it centralizes LLM access with your data kept private.

Vane

★ 35,615

AI-powered search engine (alternative to Perplexity AI).

Khoj

★ 35,585

Khoj is an AI 'second brain' that answers from your documents and the web, with agents and automations. Self-hosted, it keeps your knowledge base and searches completely private.

Onyx Community Edition

★ 30,793

Chat UI that works with any LLM. It comes loaded with advanced features like agents, web search, RAG, MCP, deep research, Connectors to 40+ knowledge sources, and more.

Local Deep Research

★ 8,689

AI-powered deep research tool with multi-source search (arXiv, PubMed, web), PDF text extraction, and encrypted local storage.

Agenta

★ 4,279

LLMOps platform for prompt management, LLM evaluation, and observability. Build, evaluate, and monitor production-grade LLM applications with collaborative prompt engineering.

LLM Harbor

★ 3,127

Containerized LLM toolkit. Run LLM backends, APIs, frontends, and additional services via a concise CLI.

LLMKube

★ 163

Kubernetes operator for self-hosted LLM inference with pluggable runtimes (llama.cpp, vLLM, TGI, Ollama, vllm-swift), multi-GPU sharding, NVIDIA CUDA + Apple Silicon Metal support, and OpenAI-compatible API.