Everyone Should Know SIMD
AIエージェントのための検索
2026年のソフトウェア開発を考える(2026/07版) / Agentic Software Engineering 2026-07 Findy Edition
2026年のソフトウェア開発を考える(2026/07版)
AI DevEx Conference 2026
2026年7月23日(木)
https://dev-productivity-con.findy-code.io/aidevex2026
『動くだけ』のその先へ — AI駆動開発で品質と速度を両取りする温故知新な新手法 / Beyond Just Vibe Coding - Combining Classic Principles with AI-Driven Development
thesysdev/openui: The Open Standard for Generative UI
The Open Standard for Generative UI. Contribute to thesysdev/openui development by creating an account on GitHub.
Pushing software engineering limits with “napkin math”
Turbopuffer cofounder Simon Eskildsen on the benefits of longer tenure, using first principles to build durable software – and why founders should be cautious when raising VC money
The Pulse: New trend - concern about massive increase in code review load
Top of mind for engineering leaders: what to do about the growing code review load, and how devs are starting to review code less thoroughly than before? Many questions, but few proven solutions.
svkozak/pi-acp: ACP adapter for pi coding agent
ACP adapter for pi coding agent. Contribute to svkozak/pi-acp development by creating an account on GitHub.
pnpm/update
Contribute to pnpm/update development by creating an account on GitHub.
anthropics/html-effectiveness: HTML effectiveness examples
HTML effectiveness examples. Contribute to anthropics/html-effectiveness development by creating an account on GitHub.
Ep 02 - “I’ve Never Seen a Model Say ‘This File Is Getting Too Big'
Recorded July 17, 2026. We settle the model-access bet. We talk about how the labs talk to us, plus extend an open invite for OpenAI, Anthropic, SpaceX, and ...
IgorWarzocha/pi-clawa: Everybody has their Claw and so do I
Everybody has their Claw and so do I. Contribute to IgorWarzocha/pi-clawa development by creating an account on GitHub.
pi-clawa — OpenClaw-ish, still Pi
An OpenClaw-style personal agent built directly into Pi, with a living home and warmth pass that keep its voice intact.
I Stopped Choosing Which Model Writes My Code
I stopped choosing which model writes my code. Now baro routes it — frontier to plan, cheap to build. Here's the safety net that made trusting the cheap one work.
jigjoy-ai/baro: A CLI that turns a goal into a pull request - and a sandbox for testing concurrent AI coding agents on the Mozaik runtime.
A CLI that turns a goal into a pull request - and a sandbox for testing concurrent AI coding agents on the Mozaik runtime. - jigjoy-ai/baro
An Eval Harness for Agent Skills: How We Change Behavior on Purpose
Stop shipping agent skills on vibes. Same prompts, three real repos, two skill versions, one blind judge. Here's the harness that tells you if a change worked.
そのスキルは本当に効いているか:ON/OFF評価で「呼ばれたか・役立ったか・割に合ったか」を測る|kagaya
サマリ 同じタスクを「スキルなし」と「スキルあり」で試し、差を測る 最初は2〜3件の合格条件を決めた小さな評価から始める スキルを追加・変更・削除するときは、呼ばれたか・役立ったか・割に合ったかを分けて確認する 最初のON/OFF評価 会議の文字起こしから、決定事項、担当者、期限を抜き出す議事録スキルを作ったとします。一度使って読みやすい議事録ができても、スキルが効いたとは限りません。 スキルなしでも作れたのか、たまたま簡単な会議だったのかを区別できないからです。 自分で書いたSKILL.mdには、どうしても判定が甘くなります。そこで同じタスクをスキルなしと
TIFナビ — TOKYO IDOL FESTIVAL 2026
タイムテーブルから自分だけのプランを組み、ステージ間の移動が間に合うかを自動判定。オフライン対応。
A guide to cloud software factories for engineering leaders
Software development is shifting from interactive coding agents to cloud software factories — systems that automate major parts of the SDLC while improving security, compliance, and measurable ROI.
Zach Lloyd on X: "How to build a self-improving code review agent" / X
humanlayer/12-factor-agents: What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? - humanlayer/12-factor-agents
anomalyco/rift
Contribute to anomalyco/rift development by creating an account on GitHub.
iurysza/herdr-tab-smart-rename: Generates context-aware workspace and tab names for Herdr.
Generates context-aware workspace and tab names for Herdr. - iurysza/herdr-tab-smart-rename
Matt Pocock on X: "1. Delete the docs you create to explain your code 2. Take the tokens you save on updating those docs 3. Spend them on making your code self-explanatory" / X
2. Take the tokens you save on updating those docs
3. Spend them on making your code self-explanatory
GitHubとMicrosoft APMで作る、Claude Code・Codex共通の社内Marketplace
TinyFish - Enterprise Infrastructure for AI Web Agents
TinyFish provides enterprise infrastructure for AI web agents. Run hundreds of websites simultaneously to navigate, authenticate, extract data, and automate web workflows with a fully serverless architecture.
Puter.js - The Backend for AI-Generated Apps
Puter.js is the backend for AI-generated apps. Use your existing AI coding tool to build production-ready apps with up to 90% fewer AI tokens. Auth, cloud storage, database, OpenAI, Claude, Gemini, Grok, Kimi, DeepSeek, and more, all through a single JavaScript library. No API keys. Zero setup.
July 2026 - React Aria
React Aria is now available as a component base in shadcn/ui.
dx-styles/dx-styles: Compiler-backed CSS-in-TS for zero-runtime, deterministic styling in design systems.
Compiler-backed CSS-in-TS for zero-runtime, deterministic styling in design systems. - dx-styles/dx-styles
dx-styles — Zero-runtime CSS-in-TS for design systems
Compiler-backed CSS-in-TS: zero runtime, deterministic class names, recipes, token contracts, and compile-time RTL.
