Item logo image for Waffy - AI Copilot for Web

Waffy - AI Copilot for Web

waffy.io
4.8(

10 ratings

)
ExtensionTools141 users
Item media 3 (screenshot) for Waffy - AI Copilot for Web
Item media 4 (screenshot) for Waffy - AI Copilot for Web
Item video thumbnail
Item media 2 (screenshot) for Waffy - AI Copilot for Web
Item media 3 (screenshot) for Waffy - AI Copilot for Web
Item media 4 (screenshot) for Waffy - AI Copilot for Web
Item video thumbnail
Item media 2 (screenshot) for Waffy - AI Copilot for Web
Item video thumbnail
Item media 2 (screenshot) for Waffy - AI Copilot for Web
Item media 3 (screenshot) for Waffy - AI Copilot for Web
Item media 4 (screenshot) for Waffy - AI Copilot for Web

Overview

Automate your browser with AI. Browse, click and complete multi-step workflows with models you like. Free and open source.

Waffy is a free, open-source AI copilot for the web. It runs entirely in your browser. No backend and no account. Open it from the toolbar or press Ctrl+I (Cmd+I on Mac). It sits in the side panel next to the tab you are already using. Tell it what you want in plain language. It reads the page, looks at the screen when the layout matters, and can search, research, or carry out a workflow while you keep working. Ask a question, get a summary, or extract what you need. Right-click any page and choose Summarize this page. Type @ to include another open tab, or /search, /research, or /automate to pick a mode. Attach an image, a text file, or a PDF. Pin prompts you reuse. Chat history stays on this device. Search, Research, and memory are on by default. Search looks up a live answer, reads a relevant page, and answers from it. Research goes further, using the current page, a screenshot when it helps, and more searches when the page is not enough. Memory saves lasting facts from your chats, such as your name, work, preferences, and projects, and uses them later. Facts stay on this device. You can read, delete, or reset them in Settings. Passwords, payment details, and one-off tasks are left out. Automation is off until you turn it on. Then Waffy can fill forms, click through a flow, or gather information across sites. It plans the steps, then clicks, types, drags, scrolls, and opens or switches tabs. No scripts. A vision model works best for the step that clicks and types. Bring your own model. Add an API key for a cloud provider you already use. Keys stay in this browser, and requests go directly to the provider you choose. You can also use a built-in browser model, such as Gemini Nano in Chrome, or a local server such as Ollama or LM Studio. Assign a different model to chat, search, research, planning, execution, and checking the result. Your API keys, settings, chats, and memory stay in this browser. Contribute and star on GitHub: https://github.com/upzare/Waffy

Details

  • Version
    1.3.7
  • Updated
    November 19, 2026
  • Size
    17.32MiB
  • Languages
    English
  • Developer
    Website
    Email
    support@waffy.io
  • Non-trader
    This developer has not identified itself as a trader. For consumers in the European Union, please note that consumer rights do not apply to contracts between you and this developer.

Privacy

Manage extensions and learn how they're being used in your organization

Waffy - AI Copilot for Web has disclosed the following information regarding the collection and usage of your data. More detailed information can be found in the developer's privacy policy.

Waffy - AI Copilot for Web handles the following:

Location
User activity

This developer declares that your data is

  • Not being sold to third parties, outside of the approved use cases
  • Not being used or transferred for purposes that are unrelated to the item's core functionality
  • Not being used or transferred to determine creditworthiness or for lending purposes
Search
Clear search
Close search
Google apps
Main menu