5 items
Teach an agent a browser workflow with mouse paths, semantic clicks, and checkpoints. Show an agent a workflow once instead of writing a script. Orivael Mouse Teacher records a browser workflow you demonstrate — mouse path, what you clicked, where you navigated, and the results you expect — and exports it as a workflow.json plus an agent-handoff.md that any AI agent can use as a worked example. HOW IT WORKS 1. Open the page where the workflow starts and click the Mouse Teacher button. 2. Describe what you are teaching and press Start new capture. 3. Do the workflow. A teal cursor follows your pointer and flashes on each click. 4. At any useful result, open the popup and add a checkpoint: what should the agent verify here? 5. Press Stop, then Review & export. Give the two files to your agent. WHAT IT CAPTURES • Pointer movement, normalized to the viewport, about 12 samples a second • Click targets by meaning: test IDs, element IDs, roles and labels, plus bounding boxes • Input-change markers with the value omitted, so the agent asks you for the parameter • Page paths, scroll position, and the Enter, Tab and Escape keys • Your checkpoints, stored as unverified human expectations WHAT IT NEVER CAPTURES • Typed values, including passwords • URL query strings and hash fragments • Anything inside containers you mark data-private or data-sensitive • Screenshots, video, audio, other tabs, or iframe interiors PRIVACY Everything stays in your browser's local storage. There is no server, no account, no analytics, and no model call. Exports are files you download yourself. Uninstalling deletes all data. Full policy: https://orivael.dev/mouse-teacher-privacy.html SCOPE This is demonstration capture, not screen recording and not automatic replay. The exported handoff tells the agent to resolve targets, ask for missing parameters, rehearse in an authorized environment, and narrate only verified results. Autonomous execution needs a separate runner such as a NodeXLoop adapter. Built by Orivael. Support: hello@orivael.dev
Sep 18, 2026
rating_count is the Chrome Web Store ratings count, not a written-review count.
Media assets
Screenshots and videos on the listing.
Has promo video
Whether the listing includes at least one video.
Languages
Declared language locales.
Developer website
Listing exposes a developer website URL.
Contact email
Listing exposes a contact email.
Keyword in name
Case-insensitive substring match in the name.
Keyword in description
Case-insensitive substring match in the description.
Keyword occurrences in description
Count of case-insensitive occurrences in the description.
Category user-count percentile
Share of same-category extensions with fewer users (null if unknown).
These are transparent listing completeness / keyword signals, not a prediction of Chrome Web Store search ranking.