Ask questions about your own documents with an AI that can run entirely on your computer.
LibreChat
One private chat window for ChatGPT, Claude, Gemini and models on your own computer.
AI helpers
MIT
What it does
LibreChat looks and feels like ChatGPT, but it is yours. You bring your own AI keys (or a free model running on your own computer) and switch between OpenAI, Anthropic, Google and many others in the same chat. It keeps your chat history on your own server, lets the whole family have accounts, and can read files, search the web and build simple helpers ("agents") with their own instructions.
- Every major AI in one familiar chat window, plus free local models
- Accounts for each family member, with optional spending limits
- Chat with your files, search the web and build simple helpers
- History stays on your own server; search all past chats
Great for: Households and small groups who want one private ChatGPT-style app for several AI models, with their own accounts and keys.
- LicenceMIT
- Where it runsOnline (from $16/month) · Your computer (free)
- Built withtypescript, javascript
- Your dataStays in your own copy
- Sourcedanny-avila/LibreChat
Ways to use it
Choose one when you tell your AI. It sets everything up with you, in plain words.
- Online with Elestio from $16/monthFully managed hosting on your own private server, with automatic backups, updates and monitoring. Third-party host.
- On my own computerFreeYour AI installs what it needs and explains each step. It works while your computer is on.
Hosts are independent companies, not BespokeAI. You sign up and pay them directly. We may earn a referral fee, which never changes your price.
How people are using this project
Examples of what people ask their AI to do with LibreChat. Start from one, or just tell your AI and it will ask what you'd like.
-
“Set up LibreChat for my family of four on our home computer. Everyone gets their own login, nobody else can sign up, and it's called 'Patel Family AI'.”
Start with this idea -
“I don't want my chats going to any company. Connect LibreChat to Ollama on this computer and hide the cloud providers.”
Start with this idea -
“Make a 'Homework Helper' for my 12-year-old that explains things step by step, never just gives the answer, and is the only option she sees.”
Start with this idea -
“We share one OpenAI key. Give each family member a monthly allowance so nobody runs up a big bill.”
Start with this idea -
“Let LibreChat search the web and show its sources, using a SearXNG search I run myself instead of a paid service.”
Start with this idea -
“My dad is 80. Make a start screen with huge text, three big buttons for things he asks often, and nothing else to click by mistake.”
Start with this idea
Can I trust it?
- MIT. Very permissive. You can use, change and share it, even commercially, as long as you keep the copyright notice. No obligation to publish your changes. (The root package.json says "ISC", but the LICENSE file at the pinned commit is MIT.)
- Your data: stores personal data, on your own device or server. Accounts, conversations, presets, agents and memories in MongoDB (./data-node). Uploaded files and images in ./uploads and ./images. Document chunks for file search in the pgvector database (pgdata2 volume). Settings in .env and librechat.yaml.
- Other services: AI model providers (OpenAI, Anthropic, Google, Mistral, OpenRouter, Groq, DeepSeek…) (optional, pay-per-use with your own API key; each person can also enter their own key); Ollama or another local OpenAI-compatible server (optional, free (uses your own computer)); Embeddings for file search (RAG API, OpenAI by default) (optional, small pay-per-use, or free with a local embeddings model); Web search providers (e.g. Serper, SearXNG, Firecrawl, Jina) (optional, free tiers or pay-per-use; SearXNG is free and self-hosted); Email (SMTP) (optional, free with most providers)
- Pinned version
eac18f4. Every handover uses exactly this code, which we've reviewed. - Turn off ALLOW_REGISTRATION after creating your accounts, and use HTTPS behind a reverse proxy before opening it to the internet.
- Messages, uploaded files and memories are sent to whichever AI provider you pick for that chat. Use Ollama or another local model for anything you don't want to leave your home.
- API keys live in .env (and per-user keys encrypted with CREDS_KEY). Never paste .env into an AI chat, and set your own JWT and CREDS secrets before real use.
- Agents with code execution, MCP tools or attached workspaces can take real actions. Only enable them for people you trust.
Did it work for people?
No reports yet
Be the first to tell others how it went.
More for ai helpers
A personal AI that knows your notes and documents and can research the web for you.
Ask a question, get a written answer with sources, from a search engine you run yourself.