Big-AGI is a client-first web application, which means it prioritizes speed and data ownership compared to cloud apps. Your API keys, chat history, and settings live in your browser's local storage, not on cloud servers.
You can use Big-AGI in two ways:
This guide explains how the open-source version handles your data. You can verify everything in the source code.
Within Big-AGI almost all chat/keys data is handled client-side in your browser using two standard browser storage mechanisms:
The Big-AGI backend mainly passes requests to AI services (OpenAI, Anthropic, etc.). It doesn't store your data, except for the chat-sharing function if used.
You can see your data in your browser's local storage and IndexedDB - try it yourself:
Storing data in your browser means:
AI interactions in Big-AGI, such as chats, AI titles, text to speech, browsing, flow through three components:
You run the server. Your data only leaves when making AI requests. The keys and chats are under your control and pass through your code, and are sent to the upstream AI services on a per-request basis.
Your data passes through the hosted Big-AGI edge network to reach AI services. The keys and chats pass through Big-AGI's edge network to reach the AI services on a per-request basis, and then are send to the upstream AI services.
Basic Security:
When Running Your Own Server:
Your API keys and chats stay in your browser. The server only passes requests to AI services.
Use big-agi.com for convenience, or run it yourself for full control.
Need help? Join our Discord or open a GitHub issue.