Suede AI Skills Directory
browser-use vs agent-browser
A comparison selected for Web Scraping and Browser Automation, Browser Agents and Computer Use. Compare the task description and license first, then use the score breakdown to inspect their published files.
Quality snapshot: 2026-10-22. Install counts: skills.sh, 2026-11-08. This pair was selected from shared topics and recorded installs; it is not a claim about joint search volume.
At a glance
| Evidence | browser-use (browser-use/browser-use) | agent-browser (vercel-labs/agent-browser) |
|---|---|---|
| Listing | browser-use | agent-browser |
| Task | Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(use_cloud=True)), Playwright, Puppeteer or any CDP client. | Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools. |
| Quality score | 69/100 · D | 75/100 · C |
| License | MIT | Apache-2.0 |
| Cost lane | free-open-source | free-open-source |
| Recorded installs | 99,223 | 1,351,437 |
| Report | Score report | Score report |
Where the scores differ
| Component | browser-use | agent-browser |
|---|---|---|
| Structural checks | 48 / 56 | 56 / 56 |
| Description length | 5 / 5 | 1 / 5 |
| Boundary clause | 0 / 4 | 0 / 4 |
| Example request | 0 / 3 | 3 / 3 |
| Instruction depth | 7 / 7 | 4 / 7 |
| Reference files | 0 / 3 | 0 / 3 |
| Bundled scripts | 0 / 2 | 0 / 2 |
| Recent maintenance | 9 / 9 | 9 / 9 |
| Curated-list citations | 0 / 7 | 0 / 7 |
| Tool permissions declared | 0 / 2 | 2 / 2 |
| Compatibility declared | 0 / 2 | 0 / 2 |
agent-browser has the higher structural-quality score by 6 points. Use the task descriptions above to judge fit. These scores do not measure runtime performance or security.
Inspect before installing
browser-use and agent-browser link to their publishers, licenses and installation routes. Read the source before giving either skill access to your project.