AI · Early access

LocalAI hosting on your own server

A drop-in, OpenAI-compatible API for running AI models locally.

Early access. Join the list and we email you when LocalAI opens on VPS.

What LocalAI does

LocalAI exposes an OpenAI-compatible REST API in front of locally run text, image, and audio models, so existing OpenAI-client code can point at a self-hosted backend instead. It supports many model formats and runs without a GPU, though performance benefits from one. It supports GGUF, ONNX, and several other model formats, so existing quantized models can be reused directly.

LocalAI at a glance

License: MIT
Source code: github.com/mudler/LocalAI
Website: localai.io
Runs on: Your own server (VPS)
Good to know: Runs on CPU-only hardware, but needs a GPU for good speed with larger models.

Self-hosted OpenAI API replacement
Offline text and image generation
Cost control on AI inference

LocalAI, connected to the rest of your business

On your domain
LocalAI answers at an address like localai.yourbusiness.com, with SSL and daily backups switched on.
Mail from your address
LocalAI sends its emails from your CloudWish business mailbox. Business email
AI with a cap you set
Give LocalAI its own AI key with a monthly spend cap. Usage shows as its own line on your bill. AI in your apps (early access)