Runi

AI sidebar agent to understand, transform, and automate the current page—with your approval

Runi is a controllable AI agent in your browser side panel. It helps you understand and work with the page you are currently viewing without switching context. Your page, your way. Use Runi to: • Summarize the current page and ask page-grounded questions. • Inspect page evidence such as readable text, HTML, DOM structure, scripts, stylesheets, and computed styles for technical analysis. • Request page transformations and browser-page actions. Before write actions run, Runi shows the planned operation and asks for your approval; that decision applies to the current turn. • Connect your own OpenAI-compatible or Anthropic-compatible AI provider, including a custom endpoint. Runi is local-first: provider settings, API keys, interface preferences, and conversation history are stored in your browser. Runi has no developer-operated backend, analytics, or advertising SDK. When you initiate an Agent request, you direct Runi to transmit your API key, current prompt, recent conversation context, and relevant current-page tool results directly from the extension to the AI provider endpoint you configured as needed to fulfill that request. That provider processes the request under its own terms and privacy policy. Runi reads or changes a page only after you open the product and initiate an action. Before the first write action in a turn, Runi asks for approval and reuses that decision only for that turn. Brand upgrade notice: Runi uses a new local data namespace and does not read Aluminum settings or conversations. After upgrading, configure your provider and API key again.