Media
4 items
Description
Browser-native AI assistant with chat, page context and local/cloud providers. Pagenova is a browser-side panel AI assistant for questions about the content on your screen. Select text on a page, choose one or more open tabs, attach a document or image, or capture a screenshot. Pagenova sends only the context you choose with your question, then shows which sources were used in the answer. Use a local Ollama model, or connect to OpenAI, Anthropic, Google Gemini, or another OpenAI-compatible provider. Longer pages and documents can be chunked and retrieved when they don't fit cleanly in a model's context window. Pagenova also supports optional web search through DuckDuckGo or Tavily. You can upload PDF, DOCX, TXT, CSV, Markdown, and common code files. You can attach, paste, drag into the panel, capture from the active page, or select images from a webpage. Pagenova warns before sending an image to a model that does not support vision. The side panel supports streamed responses, stopping a response in progress, follow-up questions, saved conversation history, Markdown export, light and dark themes, and an in-browser embedding option for retrieval. Pagenova has no account system, analytics, advertising, or tracking. Settings and chat history stay in browser storage. API keys are stored only for the current browser session and are sent only to the provider you select. Page text, selected text, documents, images, and screenshots are read only when you choose them. If web search is enabled, your query is sent to the selected search provider.