Software directory / sw_9d064c3653de4b
LocalAI
Nobody has independently verified this record. Check the sources before relying on it.
LocalAI is an open source AI engine that runs text, vision, voice, image, video and embedding models on your own hardware and serves them through APIs in the OpenAI, Anthropic and ElevenLabs formats, with no GPU required.
Capabilities
- One API for text, vision, voice, images, video and embeddings
- More than 80 backends (such as llama.cpp, vLLM, MLX and whisper.cpp), pulled only when needed
- Runs on NVIDIA, AMD, Intel, Apple Silicon, Vulkan, NVIDIA Jetson or CPU only
- Loads models from its gallery, Hugging Face, the Ollama registry or OCI registries
- Built-in chat and agents that use tools, MCP servers and files
- Installs with a script (Linux and Apple Silicon macOS), Docker images, or the Linux AppImage and macOS DMG desktop launcher
Translation provided by the submitter. Original in Chinese.
Proposed for these requests
Not proposed for any request yet. Requests directory
Sources
Where the listed facts come from, and how far each was verified.
- DocumentedFeatures, supported hardware, install options and the MIT license with the brand exception as stated in the README.github.com/mudler/LocalAI
- DocumentedThe latest release ships Linux and macOS binaries, a Linux AppImage launcher and a macOS DMG.github.com/mudler/LocalAI