PacketLens
PacketLens is a pure front-end, offline pcap analysis tool that runs entirely in the browser, supporting deep protocol decoding, HTTPS decryption, and million-packet instant loading without any backend.
它现场演示了 AdaL Engineer 通过单个提示自主克隆登录页面,展示了循环工程的实际威力。
Learn to build with AdaL — the agent that engineers loops. From vibe coding to vertical agent SaaS.
| Class | Topic | Slides |
|---|---|---|
| Class 1 — Beyond Loop Engineering | Vibe coding → loop engineering → AdaL's full offering → vertical agent SaaS | HTML · MD |
| Class 1 — AdaL Setup | Install, launch (engineer vs worker), model recommendations | HTML |
| Class 2 — Building Custom Agents | Custom prompts, custom tools, AdaL Cloud, SDK, live demo | HTML · MD |
Open any slide deck in your browser:
open slides/class-1-beyond-loop-engineering.html
The AdaL Engineer agent autonomously cloned a landing page end-to-end — research, design extraction, implementation, and visual verification — all driven by the loop-engineering workflow taught in Class 1.
The prompt we used for this:
Clone the hero section of the landing page, https://www.hyperspell.com/ , put it inside of hyperspell-clone, needs to be exactly the same, from animation, content, font, color, styling, everything, pixel level, and video level including all effects
You have the two docs to refer to:
1. clone_guide_v2.md (operational guide + appendices) — the one you follow
2. clone_landing_page_101.md (deep reference) — the one you consult when stuck
Use MiniMax M3 Browser Use for both evaluator and builder
The screenshot shows the agent's autonomous cloning workflow in action.
slides/
├── class-1-beyond-loop-engineering.html # 12-slide deck
├── class-1-beyond-loop-engineering.md # markdown source
├── class-1-adal-setup.html # 5-slide setup deck
├── class-2-custom-agents.html # 10-slide deck
├── class-2-custom-agents.md # markdow
根据分类、Topic 和编程语言匹配的相似项目。
PacketLens is a pure front-end, offline pcap analysis tool that runs entirely in the browser, supporting deep protocol decoding, HTTPS decryption, and million-packet instant loading without any backend.
An interactive learning system that turns the 47-page Kimi K3 technical report into a single offline HTML file with running algorithms, 3D visualizations, spaced repetition quizzes, and a smart highlighting QA tool.
An interactive 3D visualization of three human cell types using Three.js, WebGL particles, and custom GLSL shaders, allowing users to rotate, zoom, morph, and explore annotated structures.