npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@gpzhang2001/sharpkit-browser

v0.2.2

Published

view_image screenshot return over the attachment pipeline; browser driving stays exec_command (agent-browser CLI in the sandbox image)

Readme

@gpzhang2001/sharpkit-browser

view_image:把沙箱内的截图以图像内容块回传给模型。浏览器驱动本身不经独立工具——agent 经 exec_command 调容器内 agent-browser CLI,截图默认落在 /workspace/.agent-browser-screenshots/。

view_image

  • 相对路径落 screenshotDir;绝对路径必须在工作区内(strix 错误文案)
  • session.getFile(docker cp 二进制安全)读字节 → magic bytes 识别 PNG/JPEG/WebP/GIF
  • attachments 管线(mcp-client 对齐):execute 内经 resolveModelInfo 证明模型 image input 能力 → attachments.saveImages 持久化 → finalizeContent(WeakMap 投影)换入 image block;任一步失败降级为文本诊断,canonical base64 保留——视觉模型缺失不会杀扫描(strix strip_all_images_from_session 的准入侧等价)
  • maxContextImages(默认 3,strix STRIX_MAX_CONTEXT_IMAGES):每 scan 准入预算;窗口级图片剥离属 dsh compaction 层

Config

scanId、screenshotDir、maxImageBytes(5MB)、maxContextImages(3)、workspaceRoot。

测试

tests/browser.test.ts:magic bytes / 路径解析 / 预算 / canonical value / finalizeContent 投影与降级(fake sandbox + attachments + llm)。