LibreChat
A self-hosted chat app with agents, tools and model choice built in.
What it is
LibreChat is a self-hosted chat platform that looks like the mainstream AI chat products but runs on your own server. It is aimed at people who want the interface and the extras — conversations, agents, file handling, sharing — without handing their usage over to a vendor.
Its distinguishing feature is the breadth of providers: it can talk to OpenAI, Anthropic, Google, local endpoints and many others through the same UI, with per-user keys, presets and model switching. Recent versions add agents and support for MCP, the protocol used to connect models to external tools and data, so a conversation can call out to real services rather than only produce text.
It fits a team or a power user who wants one place to reach several providers and a private store of the resulting conversations. If you want the simplest possible local chat with a single model, a lighter front end will get you there faster.
Why we recommend it
Many providers, one interface
You can keep a paid frontier model for hard questions and a local model for private ones, and switch between them without leaving the page. Centralising that choice saves juggling several apps and accounts.
Agents and MCP support
The platform can wire a model to tools and external data through MCP. That turns it from a chat box into a place to run small automated workflows.
Multi-user with separate keys
Accounts, per-user API keys and conversation isolation let a small team share one deployment without sharing credentials. That is the part that usually forces people toward a paid product.
Your data stays on your server
Chats, files and configuration live in your own database. For work that touches client or internal material, that is a property you cannot buy from a hosted chat app.
How it scores
These are our editorial ratings, not benchmark results. We score on how the project behaves in practice — how long it takes to get running, how good the documentation is, how responsive the maintainers are, and how well it holds up over time. The licence and star count above are read from GitHub and are a snapshot.
Pros and cons
Strengths
- Supports a wide range of providers, including local endpoints
- Built-in agents and MCP tool integration
- Multi-user accounts with per-user API keys
- Polished UI with conversation search and sharing
- Actively developed with frequent releases
Trade-offs
- Deployment is a Docker Compose stack rather than a single click
- The number of settings means a real learning curve for administrators
- It is a chat platform, not a model runner, so you still need model backends
- Under heavy multi-user load it wants meaningful server resources
How to get it
One-line install
Prefer the terminal? Copy a command and you are done.
git clone https://github.com/danny-avila/LibreChat.git && cd LibreChat && cp .env.example .env && docker compose up -d
Source and documentation
At a glance
| Category | Local AI |
|---|---|
| Licence | MIT |
| Written in | TypeScript |
| GitHub stars | 42,985 |
| Repository | danny-avila/LibreChat |
Licence and star count were read from the GitHub API when this page was generated and are a snapshot. Check the repository for the current figure and the authoritative licence text.
Other Local AI tools
We are not affiliated with LibreChat or its maintainers. We list it because it is genuinely useful and genuinely free. If you plan to build a commercial product on top of it, read the licence on the repository first.