Bookmarks

Tokio is a runtime for writing reliable asynchronous applications with Rust. It provides async I/O, networking, scheduling, timers, and more.

Chrome 154 adds support for responsively-sized iframes, letting an iframe size itself based on the intrinsic size of its embedded document.

The ones the models write are terrible, at best just doubling total LOC. Inverting the testing approach - heavy e2e/black box/golden master, reaching for lower levels only if necessary, works better for me

Contribute to TeamWarp/effect-mq development by creating an account on GitHub.

Effect-native background jobs. Schema-typed payloads, swappable storage, at-least-once execution.

One skill unlocks 1,800+ tools & APIs. No per-tool sign-ups, no subscriptions.

Hermes Agent refactored its own codebase: 1,393 subagents over about nineteen active hours cut non-test Python by 34.4%, for roughly $19,300 in model spend against a $150k-$1.8M estimate for doing it by hand.

Native, bezeless, and blazing fast. Browse the web with vertical tabs.

Earlier this year, I believed planning was going to become the most important part of building software with AI.

AIが書いた日本語に出てきやすい単語と言い回しを、形態素解析で見つけるtextlintのプリセットを作ったので紹介します。

Predictive inline shell autosuggestions for zsh. Go daemon, no TUI, no sync - Giammarco-Ferranti/deja

Agents can finish code modernizations in months, but change management still sets the pace. Six steps to define the target, certificate, and promotion policy.

3,112字

Run ssh railway.new and get a free Linux VM in about 1.4 seconds, with coding agents preinstalled and a preview URL. No account needed. Claim it to keep it.

Ollaya downloads and serves open decision models on your own machine. Typed, calibrated answers in milliseconds, private and open source.

Effort tells your model how many resources to spend on a task. When to turn it down, when to turn it up, and why the default is the right place to start.

What effort really is and when to use which level in Claude Code, from my own tests of three builds and a deep dive into Terminal-Bench 3.0 on Opus 5.5 and Fable 5.1.

An alternative logical projection of React with 100% API compliancy but simpler implementation resulting in smaller bundle size and better performance. - TanStack/redact

A lightweight library full of beautiful loading indicators for React.

How we fully migrated github.com away from CSS-in-JS.

In seven months, the skills.sh registry grew to 1 million agent skills with nearly 280 million installs. This report uses aggregate data from that registry to examine what people teach agents, what gets installed, and what lasts.

OpenAIのドキュメントをもとにAgentの基本構成を整理し、OpenAI Agents SDKとClaude Agent SDKの違いを比較したうえで、Goで最小のAgentを実装します。

はじめに こんにちは。プラットフォームエンジニアリングチームに所属している徳富(@yannKazu1)です。 MySQL が遅いとき、まず EXPLAIN で計画を見る。見積もりが怪しければ EXPLAIN ANALYZE で実測と突き合わせる。たいていのケースはこの二つで十分で、実際自分もそれで困ったことはほとんどあ…

A malicious Firefox extension fetches its payload after installation to evade detection, steal Google session cookies, and automate account takeover.

If you run a platform with a dozen or more services behind it, you’ve probably seen this pattern. Service A checks an API key. Service B calls out to your identity provider directly. Service C has a half-finished authentication middleware that hasn’t been touched in a while. Every team solved the same problem differently, and […]

Worker Previews gives every branch its own URL, configuration, state, and observability, so you and your agents can test changes in parallel without affecting production.

Lovable’s OJ rewrites Vite’s dev server in Rust, reducing memory use and preview times as AI lowers the cost of open source reimplementation.

Klaviyo built an internal app platform on Vercel and opened it to the whole company. See how 512 employees shipped 356 apps in two weeks, how Secure Compute keeps every app on Klaviyo's own databases, and how an idea goes live in 3 minutes.