LibreChat Download: A Self-Hosted Chat App for Any AI Model
LibreChat · for Windows, macOS and Linux
Developer: LibreChat (opens in a new tab)
- Windows
- macOS
- Linux
The download link points to the program’s official source; the file is not hosted on this site. Link address: github.com
Link not working? Let us know
LibreChat is a free, open-source, self-hosted AI chat platform that brings many providers, including local models through Ollama, into one ChatGPT-style interface with agents, MCP and multi-user login. It runs with Docker on Windows, macOS and Linux and is MIT-licensed.
LibreChat gives you a familiar chat interface that you host yourself and connect to almost any AI model, from cloud providers to models running on your own machine. It is especially popular with teams that want one shared, private chat app.
What does LibreChat do?
- Many providers: Anthropic, OpenAI, Azure OpenAI, Google, Vertex AI, AWS Bedrock and any OpenAI-compatible API.
- Local models: Ollama, koboldcpp, Apple MLX and other local or self-hosted back ends.
- Agents: No-code custom agents, subagents and reusable skills, with Model Context Protocol (MCP) tools.
- Code Interpreter: Sandboxed code execution in languages such as Python, Node.js, Go, Rust and Java.
- Multi-user: Login with OAuth2, LDAP or email, plus an admin panel.
- More: Artifacts, conversation search, chatting with files and a multilingual interface.
Who uses LibreChat?
It suits families, teams and companies that want a single private chat app for several people, and enthusiasts who want to switch between cloud and local models freely.
Setting it up with Docker
You need Git and Docker (Docker Desktop is recommended). Then:
git clone https://github.com/LibreChat-AI/LibreChat.git
cd LibreChat
cp .env.example .env
docker compose up -d
On Windows, use copy .env.example .env if cp is not available. The first start pulls the images and can take a few minutes. Then open http://localhost:3080 and sign up; in a single-tenant setup the first account becomes the admin. To use another port, set PORT in the .env file.
What you need
- Software: Git and Docker.
- Resources: At least 1 GiB of RAM and 1 vCPU; with the default stack running, making 2 GB of memory available to Docker gives smoother operation. Docker Desktop has its own system requirements on top of that.
- CPU: The default MongoDB image needs a processor with AVX instructions; the documentation explains how to switch to an older image on CPUs without it.
- Models: LibreChat itself does not run models and needs no GPU. Local models need their own engine, such as Ollama, with suitable hardware.
LibreChat is free and open source under the MIT license.
Pros
- One interface for cloud and local models
- Multi-user login and admin panel
- Agents, MCP and a code interpreter
Cons
- Needs Docker and some setup
- Does not run models by itself
Frequently Asked Questions
Can LibreChat use local models?
Yes. It can connect to local engines such as Ollama and koboldcpp, or any OpenAI-compatible server, alongside cloud providers.
Which address does LibreChat open on?
After docker compose up -d, open http://localhost:3080. You can change the port with the PORT setting in the .env file.
LibreChatOpen source
Download (opens in a new tab)


