LocalAI
Model Serving & MLOpsOpen‑source AI engine that runs any model (LLM, vision, voice, etc.) locally on CPU or GPU hardware without needing a cloud service.
Features
- Drop‑in API compatibility with OpenAI, Anthropic, ElevenLabs APIs
- Supports +36 backends (llama.cpp, vLLM, transformers, whisper, diffusers, MLX…)
- Runs on any hardware – NVIDIA/AMD/Intel GPUs, Apple Silicon, Vulkan or pure CPU
- Multi‑user ready with API‑key auth, quotas and role‑based access
- Built‑in autonomous AI agents (RAG, tool use, MCP, skills)
Recent releases
View all 24 releases →
Review required
v4.3.2
Mixed
Dependencies
Dependencies, Middleware, Distributed, Gallery, UI, Backend
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Install & Platforms
Install via
docker
binary
Platforms
macos
linux
arm64
