LocalAI

Drop-in OpenAI-compatible API that runs models on your own hardware.

LocalAI is an open-source, self-hosted inference server that provides a drop-in OpenAI-compatible API for running models locally. It supports multiple backends (including llama.cpp, Whisper, and diffusion models) so a single endpoint can serve text generation, embeddings, audio transcription, and image generation without external cloud services. It runs on consumer hardware and is distributed as a single binary or container.