# Note: Template blocks require a 'weight' parameter so they're correctly ordered on the landing page # Hero hero: enable: true weight: 10 template: hero backgroundImage: path: "images/templates/hero" filename: desktop: "gradient-desktop.webp" mobile: "gradient-mobile.webp" badge: text: "Open source · MIT licensed" color: primary pill: false soft: true titleLogo: path: "images/logos" filename: "logo.png" alt: "LocalAI Logo" height: 340px title: "" subtitle: | **One runtime. Every kind of AI. Your hardware.** Run text, vision, speech, sound, images, video, embeddings, reranking, and autonomous agents behind one modular stack—from a CPU laptop to a distributed GPU cluster. image: path: "images" filename: "localai_screenshot.png" alt: "LocalAI Screenshot" boxShadow: true rounded: true ctaButton: icon: rocket_launch btnText: "Get Started" url: "/installation/" cta2Button: icon: code btnText: "View on GitHub" url: "https://github.com/mudler/LocalAI" info: | A small core pulls isolated model backends on demand, so you install only what you use. Build with OpenAI, Anthropic, Ollama, ElevenLabs, and Open Responses compatible APIs—or work directly through LocalAI's UI, agents, MCP tools, and distributed runtime. # Feature Grid featureGrid: enable: true weight: 20 template: feature grid title: One runtime, across the whole AI stack subtitle: | API compatibility is the easy entry point. LocalAI also gives you multimodal inference, agents, privacy controls, model operations, and distributed execution on infrastructure you control. items: - title: Any model, any modality icon: memory_alt description: Run language, vision, speech, sound, image, video, embedding, reranking, detection, and biometric models through one runtime. ctaLink: text: learn more url: /basics/getting_started/ - title: Agents and MCP built in icon: smart_toy description: | Create autonomous agents with tools, skills, RAG, memory, citations, MCP servers, and interactive MCP Apps from the UI or API. ctaLink: text: learn more url: https://github.com/mudler/LocalAGI - title: Realtime voice and audio icon: psychology description: Build interruptible WebRTC experiences with streaming transcription, language-model output, speech, diarization, and tool calling. ctaLink: text: learn more url: https://github.com/mudler/LocalRecall - title: Drop-in compatible APIs icon: api description: Use OpenAI, Anthropic, Ollama, ElevenLabs, and Open Responses clients across the modular backend ecosystem. ctaLink: text: learn more url: /basics/getting_started/ - title: Laptop to distributed cluster icon: memory description: Start CPU-only, accelerate on common GPUs, or scale across workers with smart routing, sharding, and federation. ctaLink: text: learn more url: /basics/getting_started/ - title: Modular backend gallery icon: hub description: | Pull isolated OCI backends only when a model needs them. Install, upgrade, remove, or build your own engine without rebuilding the core. ctaLink: text: learn more url: /model-compatibility - title: Privacy you can enforce icon: security description: Keep data on your infrastructure and add PII analysis, redaction, policy middleware, authentication, roles, quotas, and audit visibility. ctaLink: text: learn more url: /basics/container/ - title: Model operations included icon: settings description: Discover capabilities, import and route models, fine-tune, quantize, monitor usage, and manage the runtime through the UI or CLI. ctaLink: text: learn more url: /basics/getting_started/ - title: Engines built by LocalAI icon: groups description: The project also develops native inference engines for speech, vision, biometrics, privacy, 3D reconstruction, and quantization. ctaLink: text: learn more url: https://github.com/mudler/LocalAI - title: Extensible icon: extension description: Easy to extend and customize. Add new models and features as needed. ctaLink: text: learn more url: /docs/integrations/ - title: Peer 2 Peer icon: hub description: | LocalAI is designed to be a decentralized LLM inference, powered by a peer-to-peer system based on libp2p. It is designed to be used in a local or remote network, and is compatible with any LLM model. It works both in federated mode or by splitting models weights. ctaLink: text: learn more url: /features/distribute/ - title: Open Source icon: code description: MIT licensed. Free to use, modify, and distribute. Community contributions welcome. ctaLink: text: learn more url: https://github.com/mudler/LocalAI imageText: enable: true weight: 25 template: image text title: LocalAI - Run AI models locally with ease subtitle: | LocalAI makes it simple to run various AI models on your own hardware. From text generation to image creation, autonomous agents to semantic search - all orchestrated through a unified API. LocalAI, created by **[Ettore Di Giacinto (mudler)](https://github.com/mudler)** and maintained by the **LocalAI team** (Ettore Di Giacinto and **[Richard Palethorpe (richiejp)](https://github.com/richiejp)**), is a Free and Open Source, community-driven project to make Free, Open AI accessible to everyone. The LocalAI stack is MIT licensed, and the models trained by LocalAI are available under the Apache 2.0 License. list: - text: OpenAI API compatibility icon: api - text: Multiple model support icon: hub - text: Image understanding icon: image - text: Image generation icon: image - text: Audio generation icon: music_note - text: Voice activity detection icon: mic - text: Speech recognition icon: mic - text: Video generation icon: movie - text: Privacy focused icon: security - text: Autonomous agents with [LocalAGI](https://github.com/mudler/LocalAGI) icon: smart_toy - text: MCP Support [MCP](https://localai.io/docs/features/mcp/) icon: api - text: Semantic search with [LocalRecall](https://github.com/mudler/LocalRecall) icon: psychology - text: Agent orchestration icon: hub image: path: "images" filename: "imagen.png" alt: "LocalAI Image generation" imgOrder: desktop: 2 mobile: 1 ctaButton: text: Learn more url: "/basics/getting_started/" # Image compare imageCompare: enable: false weight: 30 template: image compare title: LocalAI in Action subtitle: See how LocalAI can transform your local AI experience with various models and capabilities. items: - title: Text Generation config: { startingPoint: 50, addCircle: true, addCircleBlur: false, showLabels: true, labelOptions: { before: 'Dark', after: 'Light', onHover: false } } imagePath: "images/screenshots" imageBefore: "text_generation_input.webp" imageAfter: "text_generation_output.webp" - title: Image Generation config: { startingPoint: 50, addCircle: true, addCircleBlur: true, showLabels: true, labelOptions: { before: 'Prompt', after: 'Result', onHover: true } } imagePath: "images/screenshots" imageBefore: "imagen_before.webp" imageAfter: "imagen_after.webp" - title: Audio Generation config: { startingPoint: 50, addCircle: true, addCircleBlur: false, showLabels: true, labelOptions: { before: 'Text', after: 'Audio', onHover: false } } imagePath: "images/screenshots" imageBefore: "audio_generation_text.webp" imageAfter: "audio_generation_waveform.webp"