A VS Code extension that turns plain .chat.md files into editable AI chat sessions with MCP tool support across LLM providers.
- Stars
- 45,964
- Forks
- 9,453
- Open issues
- 965
- Last commit
- yesterday
What is it?
LibreChat is a self-hosted AI chat interface that brings major model providers into one browser-based UI. It supports Anthropic, AWS Bedrock, OpenAI, Azure OpenAI, Google, Vertex AI, and any OpenAI-compatible endpoint, so users can switch models mid-conversation and keep one history across them.
Beyond basic chat, it offers configurable Agents with tools, MCP servers, file search, and code execution, plus Artifacts that render React, HTML, and Mermaid content in chat. A sandboxed Code Interpreter, web search, image generation, speech input and output, and conversation search are also included.
For teams, it provides multi-user authentication through OAuth2, LDAP, or email login, along with an admin panel for managing users, roles, and configuration. Deployment is handled with Docker Compose or other self-hosting setups.
Key features
- 01Connects Anthropic, OpenAI, Azure, Google, Bedrock, and OpenAI-compatible endpoints in one interface
- 02Agents with MCP servers, file search, and code execution tools
- 03Artifacts render React, HTML, and Mermaid content in chat
- 04Sandboxed Code Interpreter supporting multiple languages
- 05Multi-user login via OAuth2, LDAP, or email with an admin panel
- 06Conversation branching, presets, and full-text message search
Use cases
- A team wanting a shared, self-hosted ChatGPT-style tool across several model providers
- Developers building custom Agents that call MCP tools and run code
- Organizations that need user access control and data kept on their own infrastructure
Quick start
- 1
Click a one-click deploy button (Railway, Zeabur, or Sealos) from the README
- 2
Follow the official documentation to set up and run the project
Things to know
- Attached code workspaces are marked as highly experimental.
- The Agent Management API is in beta.
- The README advises checking the changelog for breaking changes before updating.
Topics
FAQ
- What is LibreChat?
- Self-hosted ChatGPT-style chat platform that unifies many AI providers, with Agents, MCP support, Artifacts, and multi-user auth. LibreChat is a self-hosted AI chat interface that brings major model providers into one browser-based UI. It supports Anthropic, AWS Bedrock, OpenAI, Azure OpenAI, Google, Vertex AI, and any OpenAI-compatible endpoint, so users can switch models mid-conversation and keep one history across them.
- Is LibreChat free to use? What license does it have?
- LibreChat is open source under the MIT license. Check the license terms before using it in commercial products.
- Is LibreChat still maintained?
- Actively maintained. The last commit to LibreChat was on Oct 19, 2026.
- What can I use LibreChat for?
- A team wanting a shared, self-hosted ChatGPT-style tool across several model providers Developers building custom Agents that call MCP tools and run code Organizations that need user access control and data kept on their own infrastructure
- How do I install LibreChat?
- Click a one-click deploy button (Railway, Zeabur, or Sealos) from the README Follow the official documentation to set up and run the project
- Where can I get LibreChat?
- The source code and installation instructions are on GitHub: https://github.com/LibreChat-AI/LibreChat
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A self-hosted personal AI assistant that runs on your own devices and answers you through messaging apps like WhatsApp, Telegram, Slack and Discord.
A self-improving AI agent that creates and refines skills from experience, runs on many model providers, and works through CLI and messaging apps.
A CLI and web tool that packs an entire code repository into one AI-friendly file for feeding to LLMs like Claude or ChatGPT.
An MCP server that lets AI assistants like Claude and Cursor run web searches through a SearXNG instance you operate or trust.
Open-source platform combining AI agents and workflow automation, self-hostable or embeddable in SaaS products, with 250+ connectors.