# LocalAI LocalAI is a free, open-source, self-hosted AI engine that provides a drop-in, OpenAI-compatible API for running local models. It is open source and self-hosted, installable on Umbrel, TrueNAS and Unraid. Canonical page: https://ourlocalhost.com/app/109/localai ## Description LocalAI is a free, open-source, self-hosted AI engine that provides a drop-in, OpenAI-compatible API for running local models. It runs text, audio (including voice cloning), image and video models — including GGUF, transformers and diffusers architectures — on consumer-grade hardware, with no GPU required, and pulls each model backend only when needed. It is aimed at homelab users who want OpenAI-style inference on their own hardware, without depending on cloud services. ## Platform availability Available on 6 of 9 platforms: Unraid, TrueNAS, Umbrel, Proxmox, Helm, Mac. ## Desktop and other devices Mac. ## Health score 81/100 (Excellent), based on 5 of 5 factors. - Maintained: 100 (last commit 14 days ago) - Popular: 94 (49,451 GitHub stars) - Easy to install: 85 (6 install platforms, install notes, Docker image) - Light to run: 20 (16 GB minimum RAM, runs on ARM) - Security check: 70 (no serious findings, 7 minor, CI, tests) ## Links - Documentation: https://localai.io/basics/container/#standard-container-images - GitHub: https://github.com/mudler/LocalAI - desktop: https://github.com/mudler/LocalAI/releases/latest - Umbrel: https://apps.umbrel.com/app/localai - TrueNAS: https://apps.truenas.com/catalog/localai/ - Unraid: https://ca.unraid.net/apps/localai-043k6z40z1yla4?q=LocalAI - Official website: https://localai.io/ ## Common questions ### How do I make LocalAI reachable from my browser or apps? Map port 8080 when starting LocalAI, such as Docker's -p 8080:8080, so your browser or apps can connect. If the port is not mapped, LocalAI may be running but you cannot reach it. ### What must I install before a model can run? Install the backend the model needs, for example llama-cpp, and install at least one model with the provided command. If a backend or model is missing, requests fail because LocalAI has nothing to load. ### Where does LocalAI store model files? Command line uses ./models, Docker uses /models inside the container typically mounted to ./models, and the launcher uses ~/.localai/models. You can customize the model storage location with the LOCALAI_MODELS_PATH environment variable. ### How can I test LocalAI after setup? After starting LocalAI and installing a model, send a test chat completion request to the /v1/chat/completions endpoint. This confirms the service, model, and network path are working before connecting other apps. ### Can I point an existing OpenAI client at LocalAI? Point an existing client at LocalAI as a drop-in replacement for most OpenAI API calls. It also speaks the Anthropic, Ollama, and ElevenLabs APIs, so most tools need only a URL change. ## Alternatives - AnythingLLM: AnythingLLM is a local, all-in-one AI app for self-hosters that works with any large language model, providing document chat, retrieval-aug… - ChatGPT: ChatGPT is a generative artificial intelligence chatbot developed by OpenAI and launched in 2022. - DeepSeek: DeepSeek is a state-of-the-art AI assistant designed to provide intelligent, conversational support across diverse tasks. - Euria: Privacy-first AI assistant with chat, writing, transcription, summarization, email, and document tools, hosted in Switzerland and compliant… - GPT4ALL: GPT4All runs open-source large language models (LLMs) privately on your own hardware, providing a local chat interface and server that need… - Google Gemini: Gemini gives you direct access to Google AI. - Hermes Agent: Hermes Agent is a self-improving AI agent by Nous Research that creates and refines skills from experience, builds a persistent model of yo… - LM Studio: LM Studio is an application for running and experimenting with local large language models (LLMs) such as gpt-oss, Llama, Gemma, Qwen, and… - Lumo by Proton: Privacy-first AI assistant with zero-access encryption, no logging or profiling, open-source code, and user-controlled conversations, subje… - Microsoft Copilot: Microsoft Copilot, formerly known as Bing Chat, is an AI chat interface used to converse with Microsoft hosted OpenAI and Claude models wit… - Ollama: Ollama is a local runtime for large language models (LLMs) that provides an application programming interface (API) and command-line interf… - OpenClaw: OpenClaw is an open-source, self-hosted AI assistant gateway that connects large language models (LLMs) to Discord, Telegram, and WhatsApp,… --- Source: Our Local Host (https://ourlocalhost.com/app/109/localai), the self-hosted and open-source app directory.