LocalAI
by mudler
LocalAI is a self-hosted server that runs AI models for text, images, speech and video on your own hardware, with or without a GPU. It offers an API that works like OpenAI's, so existing apps can use local models instead of paid cloud services.
- Stars
- 50k +13 a day
- Licence
- MIT
- Runs on
- A small server
- Setup
- Moderate
- Language
- Go
- Age
- 1318 days
What you can do with it
- Run chat models locally and connect existing apps through an OpenAI-compatible API
- Generate images, speech and transcriptions from your own server without sending data out
- Set up AI agents with tools and document search, and give team members API keys with usage quotas
Could replace
- ElevenLabs
Our suggestion based on what it does, not a feature-by-feature comparison.
Make money with it
Offer setup of private, self-hosted AI assistants or document search for local businesses that cannot send data to cloud providers.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Replace per-token cloud AI fees with a self-hosted model for drafting, summarising and support tasks
- Keep customer or confidential documents private by processing them on your own machine rather than a third-party service
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Install by running a Docker container (CPU or GPU versions), or on macOS by using the DMG download, then load models with the local-ai command.
Follow the official instructions in the project README.
Things to check
- Larger models run slowly without a GPU
- The macOS app is not signed by Apple and needs a manual command to open
- Some features, such as vllm.cpp, are in alpha
Checked 27 Oct 2026. Summary drafted by AI from the project's README.
