LocalAI

MIT self-hosted OpenAI-compatible engine for any model

AI Agents / Agents · OSS/MIT · 49.6k

Reviewed 2026-10-18 · last push 2026-10-19 · repo checked 2026-10-19

What's Good

MIT (mudler/LocalAI), release v4.11.0 (2026-10-02), with commits daily. A small core that pulls backends only when a model needs them, wrapping engines like llama.cpp, vLLM, whisper.cpp, stable-diffusion and MLX in separate images. Drop-in for apps that already speak the OpenAI API. ★~49.6k.

The Catch

It gained about 265 stars a week over 3.5 years, but it is a long-running, real project, not a hype spike. Performance depends on your hardware and the backend you choose, and configuring models takes more work than Ollama.

Verdict

The broadest self-hosted, OpenAI-compatible model server.

Embed

Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.

Markdown

[![Reviewed on Stack Gems](https://stackgems.com/badge/localai.svg)](https://stackgems.com/gems/localai)

HTML

<a href="https://stackgems.com/gems/localai"><img src="https://stackgems.com/badge/localai.svg" alt="LocalAI reviewed on Stack Gems" height="20"></a>

AI Agents →

Related