~/tools/librechat
LibreChat
tool

LibreChat

LibreChat is an open source AI chat platform you can self-host — a ChatGPT alternative that puts OpenAI, Claude, Gemini, Ollama, and dozens of other models behind one interface, with agents, code execution, and multi-user auth built in.

What is LibreChat?

LibreChat is an open source AI chat platform that lets you talk to many large language models from a single, ChatGPT-style interface. It connects to OpenAI, Anthropic Claude, Google Gemini, AWS Bedrock, Mistral, Groq, DeepSeek, OpenRouter, and local models through Ollama, so you bring your own API keys instead of paying for one vendor’s app. It is MIT-licensed and built to be self-hosted.

What is LibreChat best for?

LibreChat is best for individuals, teams, and organizations that use more than one AI provider and want a single private interface for all of them. It suits people who already hold API keys, run local models, or need enterprise authentication and multi-user accounts — and anyone who wants ChatGPT-class features on infrastructure they control rather than a vendor’s cloud.

What can LibreChat do?

  • Connect dozens of providers — OpenAI, Azure OpenAI, Anthropic, Google, Vertex AI, AWS Bedrock, Mistral, Groq, Cohere, DeepSeek, OpenRouter, Ollama, and any OpenAI-compatible endpoint — and switch models mid-conversation.
  • AI Agents — build no-code custom assistants and share or install them from a marketplace, with Model Context Protocol (MCP) tool support.
  • Code Interpreter — run sandboxed code in Python, Node.js, Go, C/C++, Java, PHP, Rust, and more.
  • Code Artifacts — render React, HTML, and Mermaid diagrams inline from model output.
  • Image generation and editing plus multimodal file uploads for chatting over documents and images.
  • Web search with customizable retrieval and reranking.
  • Multi-user authentication — OAuth2, LDAP, and email login, with support for GitHub, Azure AD, AWS Cognito, and Keycloak.
  • Speech-to-text and text-to-speech, conversation import/export (from ChatGPT and Chatbot UI), message search, and 30+ interface languages.

Where does LibreChat fall short?

LibreChat is a chat front end, not a governance suite — it provides technical controls like SAML, OIDC, and encrypted storage but no vendor-managed compliance (no published SOC 2, ISO 27001, or HIPAA BAA), so regulated teams take on that work themselves. Its role-based permissions are still limited: by default everyone sees the same UI and model list unless you edit config files. And because you supply every model API key, costs, rate limits, and usage tracking are on you rather than bundled into a subscription.

Is LibreChat free?

Yes. LibreChat is fully open source under the MIT license and free to self-host — you pay only for your own server and the model API calls you make. Pointing it at a local model through Ollama means those conversations cost nothing beyond your hardware. There is no paid “pro” tier or open-core upsell; the entire project is free.

What does LibreChat replace?

LibreChat is most often used as a ChatGPT alternative — a self-hostable interface where you bring your own keys and reach many models instead of paying for ChatGPT Plus or ChatGPT Enterprise and one vendor’s models. It overlaps with other open source chat front ends like LobeChat and Open WebUI; the practical differences are LibreChat’s enterprise auth options, built-in code interpreter, and permissive MIT license.

FAQ

Is LibreChat open source? Yes. LibreChat is released under the MIT license, one of the most permissive OSI-approved licenses, so you can self-host, modify, and use it commercially without restriction. The full source is public on GitHub.

Can I self-host LibreChat for free? Yes. You can deploy it free with Docker on your own server, or on platforms like Railway, Zeabur, and Sealos. The software is free; you pay only for infrastructure and the model API keys you connect.

Is LibreChat a good ChatGPT alternative? It is, if you want multi-model access, your conversations on your own server, and enterprise login options. It mirrors ChatGPT’s interface and adds agents and a code interpreter, but you manage your own API keys and costs rather than a flat monthly subscription.

What do I need to run LibreChat? A basic deployment needs Docker (or a Node.js host) plus at least one model API key, or a local Ollama instance. It uses a MongoDB database for conversations and accounts, and multi-user features rely on the built-in authentication setup.