browser-fuFixes browser automation failures. Snapshot-first workflow + API discovery behind any website UI. Use when: 'browser not working', 'can't click', 'flaky UI',...
Install via ClawdBot CLI:
clawdbot install whooshinglander/browser-fuGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://example.com/data-pageAudited Apr 16, 2026 · audit v1.0
Generated May 13, 2026
A market researcher needs to extract product pricing and reviews from a competitor's e-commerce site. Instead of battling dynamic UI elements, they snapshot the page to get stable element refs and use browser act to collect data reliably. This avoids flaky selectors and handles JavaScript-heavy SPAs.
A QA engineer automates testing of a multi-step checkout process on a SaaS platform. They follow the snapshot-first workflow to verify each step's state, using refs to interact with forms and buttons. API discovery helps bypass UI for data validation endpoints, making tests faster and more robust.
A sales team automatically gathers profile information from a professional networking site. They use browser snapshot with refs="aria" to extract stable profile element refs, and the API discovery technique to find underlying graphQL endpoints for bulk data extraction. This reduces reliance on UI automation and handles pagination via API.
An e-commerce manager sets up a daily scraper to track price changes on competitor product pages. The snapshot-first approach ensures accurate element targeting even if the site layout changes. They use loadState: 'networkidle' to wait for asynchronous content loading, and fall back to web_fetch for simpler pages.
A business analyst automates extracting data from a legacy web portal that uses heavy JavaScript. By snapshotting the page and using exact refs, they reliably fill and submit forms without guessing element paths. API discovery helps bypass login walls by using pre-existing session profiles.
Offer structured web data extracted from public websites as a subscription service. Use Browser Fu to reliably scrape data from sites that change frequently, ensuring consistent delivery. Revenue comes from monthly or API-call-based pricing for clean, curated datasets.
Provide a SaaS platform that uses Browser Fu to automate end-to-end testing for web applications. Clients configure test flows, and the platform executes snapshot-based tests, reducing flakiness. Revenue from monthly subscriptions based on test execution volume.
A consulting service that builds custom web automation scripts for clients using Browser Fu's principles. Automate tasks like lead generation, price monitoring, or data migration. Revenue from project-based fees or hourly consulting.
💬 Integration Tip
Pair Browser Fu with web_fetch for simple pages and use API discovery for complex SPAs. Always start with a snapshot before any action to ensure you have stable element references.
Scored Jun 21, 2026
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Uses a headless browser to navigate web pages, interact with elements, and extract clean, readable text content from URLs.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
通过已登录的Edge或Chrome浏览器,利用Chrome DevTools Protocol执行JS渲染页面的导航、点击、截图及数据提取等自动化操作。
Send and receive SMS/RCS via Google Messages web interface (messages.google.com). Use when asked to "send a text", "check texts", "SMS", "text message", "Google Messages", or forward incoming texts to other channels.
High-performance browser automation for heavy scraping, multi-tab management, and precise DOM extraction. Use this when you need speed, reliability, or advanced state management (cookies/local storage) beyond standard web fetching.