LocalAI/docs/content/_index.md

+++ title = "LocalAI" description = "The open, modular AI runtime. Run text, vision, voice, image, video, agents, and more on hardware you control." type = "home" +++

Open source · MIT licensed

One runtime.
Every kind of AI.
Your hardware.

LocalAI runs text, vision, speech, sound, images, video, embeddings, reranking, and autonomous agents behind one modular stack-from a CPU laptop to a distributed GPU cluster.

Install LocalAI → View on GitHub ↗

60+ backendsCPU to clusterOpenAI · Anthropic · Ollama · ElevenLabs APIs

The runtime, not just the endpoint.

Bring the model. Choose the engine. Keep control.

ReasonLanguage models · tools · structured outputText Listen & speakRealtime WebRTC · transcription · TTS · diarizationVoice CreateImages · video · music · soundMedia SeeVision · detection · recognition · depthPerception ActAgents · MCP · skills · RAG · interactive toolsAgentic

A small core, not a giant bundle.

Backends arrive when the model needs them.

LocalAI keeps the core lean. Each backend wraps a best-in-class engine-llama.cpp, vLLM, SGLang, MLX, whisper.cpp, diffusion engines, and many more-as an isolated service pulled on demand.

• Install, update, or remove engines independently.
• Mix CPU, NVIDIA, AMD, Intel, Apple Silicon, Vulkan, and Jetson.
• Build your own backend in any language through an open gRPC contract.

Explore the architecture →

We integrate the best engines. We build new ones, too.

Inference work that moves the open ecosystem forward.

The LocalAI team develops native C, C++, Rust, and GGML engines when the available stack is too heavy, too closed, or simply does not exist yet.

See the engines we maintain ↗

Speechparakeet.cppStreaming multilingual ASR

Voicevibevoice.cppLong-form TTS and ASR

Identityvoice-detect.cppSpeaker recognition and analysis

Visionface-detect.cppRecognition and anti-spoofing

Perceptionlocate-anything.cppOpen-vocabulary detection

Privacyprivacy-filter.cppNative PII detection

3Dfree-splatter.cppPose-free reconstruction

Quantizationapex-quantMoE-aware GGUF recipes

Start on one machine. Keep going.

The same runtime from workstation to private AI fabric.

01Laptop

Run useful models locally, including CPU-only setups.

02Team server

Add authentication, API keys, roles, quotas, and usage visibility.

03Distributed cluster

Route across workers, fit models across devices, and scale with demand.

More than inference

A complete local AI control plane.

Agents built in

Create agents with MCP tools, skills, memory, RAG, citations, and streamed execution from the UI or API.

Realtime by design

Build interruptible voice experiences with WebRTC, streaming STT, LLM output, and TTS.

Privacy you can enforce

Keep data on your infrastructure and add PII analysis, redaction, policy middleware, and audit visibility.

Models under your control

Discover capabilities, import models, fine-tune, quantize, route, and monitor them in one place.

One command to begin

Run your first local AI stack.

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

Installation optionsBrowse modelsCompare backendsJoin Discord