📡 选题雷达 · AI 编程

每天自动捞这个圈子在火的东西,打好分、标好能做成啥选题。共 29 条 · 更新于 2026-06-29 14:31
🔥 本周精选 跨源最该写的几条

🆕 新冒头的工具 适合做实测 / 盘点

GitHub🔥82
Waishnav/devspace
Turn ChatGPT into Codex!
实测盘点2659★ · TypeScript
GitHub🔥74
rebel0789/codexpro
Use ChatGPT Developer Mode as a local coding agent for your repo through MCP.
实测盘点1005★ · JavaScript
GitHub🔥71
NO6KIKO/gorest-2d-animation-spritesheet-generator
Codex-assisted local 2D animation spritesheet generator and scene compositing workspace.
实测盘点1005★ · TypeScript
GitHub🔥70
raiyanyahya/recall
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code
反直觉观点610★ · Python
GitHub🔥68
joeseesun/qiaomu-goal-meta-skill
Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification,
实测盘点733★ · Python
GitHub🔥68
fivetaku/fablize
A Claude Code plugin that makes Opus behave like Fable — completion, evidence, and verific
实测盘点659★ · Python
GitHub🔥68
anthropics/launch-your-agent
Claude Code skills that take a founder from idea to a live Claude Managed Agent: interview
实测盘点556★ · HTML
GitHub🔥68
ksimback/looper
Design visual, review-gated agent loops for Claude Code before you run them.
翻车安全507★ · Python
GitHub🔥65
DanMcInerney/architect-loop
Claude Fable 5 as architect, GPT-5.5 Codex as builder, the repo as memory - a research-bac
教程玩法544★ · HTML

💬 圈子在讨论 适合做观点 / 解读

HN🔥50
Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding
观点解读22赞 · 2 评论
HN🔥48
I built Ponytrail, a local audit trail for AI coding-agent edits
翻车安全24赞 · 13 评论
Lobsters🔥42
We have Mythos at Home: GLM 5.2 beats Claude in our Cyber Benchmarks
反直觉观点11赞 · 6 评论
HN🔥41
Agentic Coding Is a Trap
反直觉观点16赞 · 11 评论
HN🔥39
Agentic coding and persistent returns to expertise
观点解读15赞 · 5 评论
HN🔥39
Ask HN: Do you find vibe coding / agentic engineering to be fulfilling?
观点解读14赞 · 14 评论

📝 值得读的文章 适合做解读 / 教程

dev.to🔥48
Gotta Earn 'Em All: The Gym Badges of Agentic Engineering (Part 1)
There's a guy who stands at the entrance to the Indigo Plateau and will not let you throug
解读19赞 · 3 评论
dev.to🔥44
Vibe Coding Bible: A Programming Paradigm for AI-Written Software
Vibe Coding Bible: Rethinking Software Architecture for AI-Generated Code For the last..
解读13赞 · 11 评论
dev.to🔥39
The Reliability Problem That Forced Us to Rethink AI Agents
A few months into building AI agents for client projects, we hit a pattern that should sou
反直觉观点8赞 · 3 评论
dev.to🔥39
Context Compaction Visualizer: See Exactly What Your AI Agent Forgot Before It Costs You
When an AI agent runs for many turns, it eventually hits context limits and must compress
成本省钱8赞 · 4 评论
dev.to🔥37
Everyone Is Building AI Agents: Nobody Is Talking About the Technical Debt
Most developers are familiar with technical debt. It's the shortcut that helps you move fa
教程玩法7赞 · 1 评论
dev.to🔥25
I Built an AI Agent That Gets Curious On Its Own
Active inference in practice: an agent that minimizes surprise develops curiosity for free
解读2赞 · 2 评论