LibreChat
Self-hosted AI chat app for teams, with many model providers
Is LibreChat open source?
Yes. LibreChat is open source software released under the MIT license and developed by LibreChat (Danny Avila and contributors). The source code is public in its official repository.
Advertisement
Overview
LibreChat is a free and open source AI chat application that you host yourself. It gives a team or household one familiar chat interface in the browser, with user accounts, while letting the administrator decide which models are available, from cloud providers to models running on your own hardware. The project was started by Danny Avila and is developed in the open on GitHub under the MIT license.
Its main strength is breadth. LibreChat supports Anthropic’s Claude models, OpenAI and Azure OpenAI, Google and Vertex AI, and AWS Bedrock out of the box, and any OpenAI-compatible API through custom endpoints. That includes local servers such as Ollama and llama.cpp, so one deployment can offer both private local models and cloud models, with each provider’s API keys held on your server instead of every user’s device.
Beyond chat, LibreChat includes agents that can use tools, file search, and Model Context Protocol (MCP) servers, and agents can be shared with specific users and groups. It supports single sign-on through OpenID Connect, which matters for organizations, and it’s typically deployed with Docker Compose.
Key Features
- Many providers in one interface — Claude, OpenAI, Azure OpenAI, Google, Vertex AI, AWS Bedrock, and custom endpoints
- Local models — Connect Ollama, llama.cpp, and other OpenAI-compatible local servers
- Multi-user accounts — Separate users and conversations, with OpenID Connect sign-in
- Agents and tools — Agents that use tools, file search, and MCP servers, shareable with users and groups
- File uploads — Attach documents to conversations and route them to the model or to search
- Self-hosted — Deploy with Docker on your own server and keep conversation data under your control
Use Cases
- Team AI chat — Give a team one shared interface without per-seat chat subscriptions
- Central API key management — Keep provider keys on the server instead of on every user’s machine
- Mixing private and cloud models — Route sensitive work to local models and other work to cloud providers
- Home labs — A family or personal AI chat front end for models running on a home server
Who It’s For
LibreChat is for teams, organizations, and home-lab users who want a self-hosted, multi-user AI chat service and are comfortable running a Docker deployment. The software is free; model costs depend on which providers you connect, and local models cost nothing beyond your hardware.
Advertisement
Frequently Asked Questions
Can LibreChat use local models?
Yes. LibreChat works with any OpenAI-compatible API through custom endpoints, so it can use models served locally by Ollama or llama.cpp alongside cloud providers.
Is LibreChat free?
The software is free and open source under the MIT license. If you connect it to paid model providers, you pay those providers for API usage.
How do I install LibreChat?
The usual route is Docker Compose on a Linux server or home lab machine; LibreChat’s documentation covers configuration, authentication, and adding model endpoints.
Similar software: AI Assistants
AnythingLLM
Private AI app for chatting with documents, with agents and local models
AnythingLLM is a free, MIT-licensed AI app for chatting with your documents using local or cloud models, as a desktop app or a self-hosted server.
Jan
Desktop AI chat app that runs models locally or connects to cloud APIs
Jan is a free, Apache-2.0 desktop app for chatting with AI models that run on your own computer, with optional connections to cloud providers.
llama.cpp
Lightweight C/C++ engine for running LLMs on local hardware
llama.cpp is an MIT-licensed C/C++ engine for running LLMs locally on CPUs and GPUs, with a command-line chat tool and an OpenAI-compatible server.
Ollama
Run open-weight language models on your own computer
Ollama is a free, MIT-licensed tool for downloading and running open-weight LLMs locally, with a command line and an API other apps connect to.
Claude
Anthropic's AI assistant for writing, analysis, and coding
Claude is Anthropic's proprietary AI assistant for writing, analysis, research, and coding, offered on the web, desktop, and mobile with free and paid plans.
Open WebUI
Self-hosted web interface for local and cloud AI models
Open WebUI is a self-hosted web interface for AI models that works with Ollama and OpenAI-compatible APIs, under a source-available license.