LocalAI

LocalAI

LocalAI is an open-source AI engine that supports running various models on any hardware.

MCPDevOpen source
Type
MCP
Transport
http
Open source
Yes
GitHub Stars
★ 47.1k
Source
mcp-github

Overview

LocalAI is an open-source AI engine that can run diverse models on any hardware, including LLMs, vision, speech, image, and video. It does not require a GPU, and each backend is independent and loaded on demand. LocalAI provides API compatibility with OpenAI, Anthropic, and ElevenLabs, supports multi-user authentication, and role-based access control. It also includes a built-in AI agent with support for tool usage, RAG, MCP, and skills. LocalAI is ideal for developers and enterprises needing to run AI models locally.

Capabilities

  • Supports multiple model types
  • Runs without GPU
  • Backend loaded on demand
  • OpenAI API compatible
  • Multi-user authentication
  • Built-in AI agent

Use cases

Running AI models locallyDeveloping multimodal AI applicationsAI services in multi-user environmentsPrivate data processing

Setup

Requires: DockerAPI Key
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

What hardware does LocalAI support?

Supports NVIDIA, AMD, Intel, Apple Silicon, Vulkan, or CPU-only.

How do I install LocalAI?

It can be installed using Docker; see the documentation for specific commands.

Related skills