Description
LocalAI is an open-source, MIT-licensed AI engine that runs language models, speech, vision, image and video generation and agents on your own hardware. Its API is compatible with OpenAI, and the site says it also speaks the Anthropic, Ollama and ElevenLabs APIs, so most tools only need a new URL. The engine behind the API can be swapped. One model can run on llama.cpp while another runs on vLLM, SGLang or MLX, and clients see the same endpoint. A small core loads each engine as a separate backend only when a model needs it. The site says LocalAI works on any hardware, including CPU-only machines, and lists support for realtime voice, speech synthesis, object detection, depth estimation and image generation. Models are available with one click from a catalog of more than 1,000. The project is on GitHub, with documentation and a blog.…
Preview
Highlights
- OpenAI-compatible API on your hardware
- Text, voice, vision and image generation
- Swappable inference backends
- Runs on CPU without a GPU
- MIT licensed
Ratings & Reviews
No ratings yet
Be the first to rate LocalAI.
People also visit
LocalAI FAQ
What is LocalAI?
An open-source AI engine that runs language models, speech, vision and image models on your own hardware through an OpenAI-compatible API.
Is it free?
Yes. It is MIT licensed, and the code is on GitHub.
Do I need a GPU?
No. The site says models run on CPU, and GPUs can be added for more capacity.
Can I use my existing code?
Usually yes. Point an OpenAI client at LocalAI, and the site says it also speaks the Anthropic and Ollama APIs.
Which models can I use?
The site says there are more than 1,000 models that you can install with one click.
What are the best LocalAI alternatives?
Popular alternatives to LocalAI include Ollama, TurboLLM and Textgen. See all LocalAI alternatives