LocalAI
Local OpenAI-compatible API for LLMs, voice, and image generation
A local OpenAI-compatible API covering LLMs, voice, and image generation; bills itself as a "drop-in replacement for OpenAI".
Run open LLMs on your own machine — no API bills, no data leaving your device.
Key features
- Open-source AI engine running LLMs, vision, voice, image, and video models
- Small core with backends pulled on demand: llama.cpp, vLLM, whisper.cpp, MLX
- Drop-in API compatibility with OpenAI, Anthropic, and ElevenLabs
- Runs on NVIDIA, AMD, Intel, Apple Silicon, Vulkan, or CPU-only
- Multi-user ready with API keys, quotas, and role-based access
Good for
- Self-hosting a private OpenAI-compatible API with local models
- Teams needing one API for many model types and hardware
Stack & tags
self-hostedopenai-compatiblemulti-modaldockerlocal-inferenceapi-server
Quick start
docker run -ti --name local-ai -p 8080:8080 localai/localai:latestFrom the project README on GitHub.
Screenshots
Screenshots from the project’s GitHub README.