Small Fish

The cover photo was taken over the weekend—fried small fish and shrimp with peppers. It was delicious and went perfectly with rice, really giving me the feeling of eating in my hometown as a child.

Record the down-to-earth trending technologies seen every week, and publish them here after screening. If you find it good, you can follow this weekly to get update notifications.

Scira: Open-source minimalist AI search engine
https://github.com/zaidmukaddam/scira
An open-source version of Perplexity + DeepSearch tools. The UI looks good. You can try it out; it supports one-click Vercel deployment.

WebAgent by Tongyi Lab
https://github.com/Alibaba-NLP/WebAgent
Tongyi Lab open-sourced a WebAgent for searching web information, including modules like WebWalker, WebDancer, WebSailor, and WebShaper. Besides the functionality, I quite like the naming. You can check out the effects.

Color Palette Generator
https://kigen.design/color
This color palette generator is perfect for my OCD. Input a color, and it automatically generates a batch of beautiful colors for you. I strongly suggest that students making AI websites stop using that blue-purple style—it’s immediately recognizable as an AI-generated site and is quite ugly. Why not add some comfortable colors you actually like?

Look at AI

LLM Fundamentals and Practice from Scratch
https://datawhalechina.github.io/happy-llm/#/
This is good: a deep understanding of LLM core principles, implementing your first large model yourself. DataWhale open-source free ebook, very simple and easy to read.

12-Factor Agents - Principles for building reliable LLM applications
https://github.com/humanlayer/12-factor-agents
The “12-Factor Agents” principles shared on GitHub are excellent. What principles can we use to build LLM-driven software that is truly usable and can be delivered to production customers? Very well written and worth learning.

Context Engineering for AI Agents: Lessons from Building Manus
https://manus.im/zh-cn/blog/Context-Engineering-for-AI-Agents-Lessons-from-Building-Manus
Manus article “Context Engineering for AI Agents: Lessons from Building Manus” is worth reading. It shares many things they learned during internal exploration.

6K / 48K / 231 / 102K, thanks for the love. Continuing to Code / Write / Share.