Best self-hosted generative artificial intelligence (genai)
[Generative Artificial Intelligence (GenAI)](https://en.wikipedia.org/wiki/Generative_artificial_intelligence) is a subset of [artificial intelligence](https://en.wikipedia.org/wiki/Artificial_intelligence) that uses generative models to produce text, images, videos, or other forms of data.
We track 14 self-hosted generative artificial intelligence (genai) projects. The median health score in this category is 90, against 12 projects rated healthy or better and none currently flagged as at risk. The table below is ordered by health score, not popularity — the most starred project in a category is frequently not the best maintained one.
| # | Project | Health | Activity | Stars | Built with | Last release |
|---|---|---|---|---|---|---|
| 1 | LobeHub Modern design AI chat framework supporting multiple AI providers, one click install MCP Marketplace and Artifacts / Thin | Thriving · 99 | 83k | Nodejs, Docker | 27 Sept 2026 | |
| 2 | Open-WebUI User-friendly AI Interface, supports Ollama, OpenAI API. | Thriving · 98 | 153k | Docker, Python | 21 Sept 2026 | |
| 3 | LocalAI Run your AI models locally and generate images and audio (alternative to OpenAI and Claude). | Thriving · 97 | 49k | Docker, K8S | 17 Sept 2026 | |
| 4 | LibreChat Enhanced ChatGPT-compatible AI chat interface supporting multiple AI providers, with multi-user auth, message search, an | Thriving · 94 | 45k | Nodejs, Docker | 23 Sept 2026 | |
| 5 | Onyx Community Edition Chat UI that works with any LLM. It comes loaded with advanced features like agents, web search, RAG, MCP, deep research | Thriving · 94 | 32k | Docker, K8S | 27 Sept 2026 | |
| 6 | Agenta LLMOps platform for prompt management, LLM evaluation, and observability. Build, evaluate, and monitor production-grade | Thriving · 93 | 4.8k | Docker | 27 Sept 2026 | |
| 7 | AnythingLLM All-in-one desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and m | Thriving · 90 | 67k | Nodejs, Docker | 22 Sept 2026 | |
| 8 | Ollama Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models. | Thriving · 89 | 182k | Docker, Python | 25 Sept 2026 | |
| 9 | Local Deep Research AI-powered deep research tool with multi-source search (arXiv, PubMed, web), PDF text extraction, and encrypted local st | Thriving · 87 | 9.1k | Docker, Python | 28 Aug 2026 | |
| 10 | LLM Harbor Containerized LLM toolkit. Run LLM backends, APIs, frontends, and additional services via a concise CLI. | Thriving · 85 | 3.2k | Docker, Shell | 25 Sept 2026 | |
| 11 | LLMKube Kubernetes operator for self-hosted LLM inference with pluggable runtimes (llama.cpp, vLLM, TGI, Ollama, vllm-swift), mu | Healthy · 74 | 217 | Go, Docker | 25 Sept 2026 | |
| 12 | GoModel AI gateway written in Go with a unified OpenAI-compatible API for multiple LLM providers, USD cost tracking, budgets, us | Healthy · 72 | 1.2k | Go, Docker | 26 Sept 2026 | |
| 13 | Vane AI-powered search engine (alternative to Perplexity AI). | Steady · 58 | 37k | Docker | 10 Apr 2026 | |
| 14 | Khoj Your AI second brain. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research | Steady · 52 | 38k | Python, Docker | 26 Mar 2026 |
Which one should you run?
If you want the safest bet on longevity, LobeHub is the best-maintained project in this category right now at 99/100. Open-WebUI is the closest runner-up (98/100) — see the side-by-side comparison.
A health score measures whether a project is alive and shipping. It does not measure whether it has the feature you need. Use it to rule options out, then compare on features.