Find tools › Open-source projects › Keep data private

LocalAI

Open-source project · by mudler

A program you run on your own hardware that provides text, image and voice AI without the cloud.

Some setupVery popular

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Generate images and voices without an online service
  • Replace OpenAI in your apps with models on your own machine
  • Chat with local models through a web page

How to start

  1. Install Docker, the main way to run LocalAI.

  2. In a terminal, run docker run -ti --name local-ai -p 8080:8080 localai/localai:latest.

  3. Open localhost port 8080 in your browser to pick and try models.

  4. On a Mac, follow the README's workaround, since the app is not signed by Apple.

Good to know. Docker is the main install route. The macOS app is not signed by Apple (the README gives a workaround command). The built-in terminal agent can read files and run commands on your machine, but asks for approval before changing anything.

Before you install

  • Checked by a personWe read what it does before listing it.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-11-18

More detail

A self-hosted server that runs text, image, voice and video models on your own hardware and exposes them through APIs compatible with OpenAI, Anthropic and ElevenLabs.

Use it when you want a single local stand-in for cloud AI APIs so existing apps can switch to self-hosted models. It downloads the right engine (llama.cpp, vLLM, whisper.cpp, etc.) only when a model needs it, and it also works without a GPU.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map