LibreChat

by LibreChatAppGet organised

Gives you a self-hosted ChatGPT-style app where you switch between many AI models

About LibreChat

A free, self-hosted chat app you open in your browser. Connect your own keys for providers such as OpenAI, Anthropic and Google, or local models, then chat, switch models mid-chat, ask about files and build agents.

For People using several AI modelsFamilies or small teamsSelf-hosting fans

Made by LibreChat

LibreChat is an open-source project developed on GitHub by the LibreChat team and a large contributor community. Its site says it is free and brings every major AI provider into one interface.

Stars: ★ 47k
License: MIT
Cost: Usage-based
Platforms: Mac · Win · Linux
Runs: Local · Self-hosted

Overview

LibreChat is a free, self-hosted chat app that you open in your browser. You connect your own keys for providers such as OpenAI, Anthropic, Google and many others, or local models through Ollama, then chat, switch models mid-conversation, ask about files, search the web and build no-code agents with tools and MCP servers. It supports several user accounts with sign-in, so a family or team can share one install. It suits people who want one chat app for many models on hardware they control.

One install puts most major AI providers behind a single ChatGPT-style screen, and you can switch models in the middle of a chat.

Try these first

Start with the first one: it is a small task you can check easily.

Ask [model A] and then [model B] the same question: [your question]. Compare the two answers.First try · uses API credits
Summarise this uploaded PDF in five bullet points: [attach file]sends file to model
Search the web for [topic] and give me three sources with links.uses web search
Create an agent that drafts replies to customer emails in a friendly tone.

Example prompts written by Agent Flows Hub.

Features

From the creator's documentation.

Feature	What it does	Runs
Model switching	OpenAI, Anthropic, Google, AWS Bedrock, Azure, OpenRouter, Ollama and more, switchable mid-chat	Provider APIs
Files	Upload images and documents and ask questions about them	Your provider
Agents	No-code assistants with tools, file search, code execution and MCP servers	Your server
Web search	Searches the internet and adds the results to the chat	Search provider
Accounts	Several users with email, OAuth2 or LDAP sign-in; the first account is the admin	Your server
History	Search all conversations, branch them, and import chats from ChatGPT	Your server

Good to know

Run one chat app for yourself or a small team and connect the AI providers you already pay for. You can switch models in a conversation, chat with files and set up agents that use tools.

Limits

LibreChat ships with no API key of its own; add your provider keys after signing in. The default Docker setup also starts MongoDB, Meilisearch and a file-search database, so give Docker at least 2 GB of memory.
On a single-tenant install the first account you register becomes the admin. Create it yourself right after the first start.

Notes by Agent Flows Hub (original project name: LibreChat), written from the creator's documentation, not from running it ourselves. LibreChat: Docker installation · LibreChat: your first chat

Stuck setting it up?

Tell us what happened. We take a look first; if it needs paid work, you get an estimate before anything starts.

Get help

How to start

Install itPaste the install request into an AI agent you already use, or run the official command yourself or follow the official guide.macOS, Linuxgit clone https://github.com/LibreChat-AI/LibreChat.git cd LibreChat cp .env.example .env docker compose up -d
Windowsgit clone https://github.com/LibreChat-AI/LibreChat.git cd LibreChat copy .env.example .env docker compose up -d
Open itFollow the first-run steps in the app.
Give it a first taskStart it with Docker, open http://localhost:3080, create your admin account, add one provider key and ask the same question to two different models.

Steps follow the creator's instructions. The request tells your agent to read them first and wait for your OK.

Before you start

A computer with macOS, Windows or Linux.
Git and Docker Desktop (or Docker Engine on Linux)
At least 2 GB of memory available to Docker
An API key from a model provider such as OpenAI, Anthropic or Google, or a local Ollama
Pay per use. The AI service it calls charges for what you use.

Details

Made by: LibreChat
License: MIT Terms
Platforms: macOS, Windows, Linux
Runs on: Your computer, Self-hosted server

View source Official docs Report a problem

For AI agents

This page as a Markdown install brief:

/en/library/librechat/install.md

Other apps

LM Studio Finds, downloads and runs open AI models on your computer in one desktop app
LobeHub Lets you build a team of AI agents that chat, write and run scheduled tasks for you
LocalMiniDrama Turns a story idea into a script, storyboard and finished short drama video on your PC
Macro Puts your team's email, chat, tasks, docs and AI agents in one linked workspace
MaxKB Builds a chat assistant that answers questions from your own documents, on your server
Maxun Turns a website into a table of data by recording a few clicks, and watches it for changes

See all 113 apps

GitHub