# LibreChat

> Self-hosted, ChatGPT-style chat UI for every AI provider

- Category: App UIs & Builders / Chat UIs
- Language: TypeScript
- Licence: MIT
- Repository: https://github.com/LibreChat-AI/LibreChat
- Website: https://librechat.ai
- Canonical page: https://ai-tldr.dev/tools/librechat/

## In short

LibreChat is an open-source chat application you run on your own server. It sits in the Chat UIs category of the App UIs & Builders tools and is open-source, written in TypeScript and licensed MIT. To get started: clone the repository.

## Overview

LibreChat is an open-source chat application you run on your own server. Its interface is modeled on ChatGPT, but instead of locking you to one vendor it connects to many AI providers at once, including Anthropic (Claude), OpenAI, Azure OpenAI, Google, AWS Bedrock, and any OpenAI-compatible endpoint such as Ollama, Mistral, Groq, OpenRouter, and Deepseek.

It is aimed at teams and individuals who want a single chat front end across multiple models without sending their conversations to a third-party SaaS. Because it supports multi-user authentication, the first account you register becomes the admin, and you can share presets, prompts, and agents with specific users and groups.

As a chat UI, LibreChat goes beyond plain messaging: it adds no-code agents, Model Context Protocol (MCP) tools, web search, a sandboxed code interpreter, image generation, and code artifacts that render React, HTML, and Mermaid diagrams directly in the chat.

## What it does

- Connects to many providers from one UI: Anthropic, OpenAI, Azure, Google, AWS Bedrock, and any OpenAI-compatible API (Ollama, Mistral, Groq, OpenRouter, Deepseek, and more)
- Build no-code custom agents with MCP servers, tools, file search, skills, and subagents, plus an agent marketplace and group sharing
- Sandboxed code interpreter that runs Python, Node.js, Go, C/C++, Java, PHP, Rust, and Fortran with file upload and download
- Code artifacts render React, HTML, and Mermaid diagrams inline in the conversation
- Multimodal file and image chat, image generation and editing, and built-in web search to enrich model context
- Multi-user authentication, presets, prompt sharing, conversation forking, and resumable streams that reconnect and sync across tabs and devices

## Getting started

The recommended way to run LibreChat locally is with Docker Compose. Clone the repo, copy the example environment file, and start the stack.

1. Clone the repository

   Get the source and change into the project directory.

```bash
git clone https://github.com/LibreChat-AI/LibreChat.git
cd LibreChat
```

2. Create your environment file

   Copy the example file to .env and edit it to add your provider API keys.

```bash
cp .env.example .env
```

3. Start the app

   Bring up the containers in the background, then open http://localhost:3080 in your browser. The first account you register becomes the admin.

```bash
docker compose up -d
```

## When to use it

- Give a team one self-hosted chat front end for Claude, GPT, Gemini, and local Ollama models instead of separate vendor apps
- Keep conversations on infrastructure you control for privacy or compliance reasons
- Build and share no-code agents that use MCP tools, file search, and the code interpreter
- Prototype quickly with code artifacts that render React, HTML, and Mermaid diagrams in the chat