Branch any AI answer into focused sub-conversations. Your chats, keys, and models are stored in your account.
Keys are stored in your account and used only by the server to call providers. They are never sent to your browser again and never called from the browser.
Pick which models appear in your model selector. Fetch the live catalog from any provider you have a key for, or add a model ID manually.
Open Settings, paste an API key from OpenRouter, OpenAI, Anthropic, Google, xAI (Grok), Groq, Mistral, or DeepSeek, then fetch that provider's catalog and activate the models you want. Active models fill every model selector.
Press Enter to send, Shift+Enter for a new line, Esc or Stop to cancel a streaming reply. Each chat remembers its model; everything autosaves to your account.
Select any text in an AI reply and click Branch into thread. A focused sub-conversation opens with full parent context. The selected text stays highlighted — click it any time to reopen. Threads nest infinitely, each layer can use a different model.
Ctrl+K searches every chat and thread. The tree icon maps all branches of the current chat. Export any chat as Markdown from the toolbar.