by Raidriar7170 · Agent Tool · ★ 57
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/Raidriar7170/browser-use-vision.gitTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 57 |
| Forks | 3 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 64/100 |
| Open Issues | 1 |
| Last Updated | 2026-06-26 |
| Created | 2026-05-20 |
| Platforms | browser, python |
| Est. Tokens | ~15k |
中文 | English 🔍 Browser-Use 视觉增强 为热门开源 browser-use 浏览器 Agent 框架提供视觉 Grounding 增强插件——让 Agent 不仅能读 DOM，还能"看见"页面。 ⚡ 一句话总结 在 DOM 完全无法解析的纯图标 UI 上，加入视觉管线后 gpt-4o 浏览器 Agent 从 ，整体客观成功率从 （+25%）。 ——所有数字来自客观校验（DOM 状态 / URL / 实时 API），绝非 Agent 自我评分。 左：纯图标音乐播放器——每个控件都是无文本/aria-label 的 ，DOM 无法解析。 右：Set-of-Mark 为 VLM 提供每个可点击元素的编号句柄。 同一套 SoM + Florence 管线，唯一变量是驱动 LLM。弱 VLM (gpt-4o-mini) 几乎无法利用 grounded...
Looking for a browser-use-vision alternative? If you're comparing browser-use-vision with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Agent that actually understands social platforms. Fast. Precise. Deep.
Browser-automation agent for Chrome — natural-language tasks executed through native tool calling, scoped Skil
let any ai agent use the local browser
any llm browsing for you in chrome
The browser tool that can stop and ask you. A 2FA code, a CAPTCHA, a choice only you can make: it asks on your
Let any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory,
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: