直近1年の AI Agent を使ってシステム開発してきた所感 - forest book
私が業務に AI Agent を活用できるようになったのは次の fukabori.fm のエピソードを聞いてからです。 iwashi さんと twada さんの話しを聞いて、ようやく ai を使った開発についての展望や方向性を自分の中で納得できた。これまで界隈の盛り上がりと周りの人の話しに対して、自分の懸念を解消できて…
The Memory Heist
How I tricked Claude into leaking your deepest, darkest secrets
emilkowalski/skills: Skills for Design Engineers.
Skills for Design Engineers. Contribute to emilkowalski/skills development by creating an account on GitHub.
Snapzy | Beautiful Screen Capture for macOS
Snapzy is a native macOS app for capturing stunning screenshots and screen recordings. Create, edit, and share beautiful visuals in seconds.
duongductrong/Snapzy: An open-source native macOS screenshot and screen recording app. A CleanShot X alternative.
An open-source native macOS screenshot and screen recording app. A CleanShot X alternative. - duongductrong/Snapzy
We Must Act Now
How Claude's values vary by model and language \ Anthropic
We analyzed 300,000 real conversations to measure the values Claude expresses across models and languages, compressed into four interpretable axes.
パスワード入力のmaxlengthで長いパスワードで登録できたつもりになってた問題2026
パスワード入力のmaxlengthで長いパスワードで登録できたつもりになってた問題2026. GitHub Gist: instantly share code, notes, and snippets.
Too many words about DIDs
Blog post: Too many words about DIDs by Steve Klabnik
最近の AI コーディングで実践している、設計を中心とした開発の進め方
AI コーディングエージェントの自律性が向上し、複数のエージェントを並行して動かすことが日常になったことで、開発の中で最も時間を使う工程が実装から設計へ移りつつあります。この記事では、設計セッション、Git worktree を使った並列実行、自律的な検証、AI によるコードレビューなど、最近の私が実践している開発の進め方を紹介します。
Libretto | Browser automation tooling for coding agents
Open-source CLI, debug agents, and browser tools for building and maintaining reliable web integrations.
saffron-health/libretto: The AI toolkit for building reliable browser automations
The AI toolkit for building reliable browser automations - saffron-health/libretto
RailsでクライアントIPを安全に取得する話 - PLEX Product Team Blog
はじめに クライアントIPの取得方法 Railsはクライアントと直接通信しているわけではない X-Forwarded-Forとは X-Forwarded-For は複数のIPが入る じゃあ X-Forwarded-For をそのまま読めばいいのか？ 一度ブラウザを経由すると信頼できなくなる Railsのrequest.…
Introducing 1Password Credential Broker | 1Password
Secure your CI/CD pipelines and AI agents with 1Password Credential Broker. Join the private beta and take the next step to unify access for humans, machines, and agents.
my-take-dev/inspired-mino-design-skills: ミノ駆動氏のWebに掲載されている資料から作成した開発スキル
ミノ駆動氏のWebに掲載されている資料から作成した開発スキル. Contribute to my-take-dev/inspired-mino-design-skills development by creating an account on GitHub.
AIによる工数削減を計測して見えた結果と考察 - ZOZO TECH BLOG
はじめに こんにちは、データシステム部MA推薦ブロックの佐藤（@rayuron）です。私たちは、主にZOZOTOWNのメール配信のパーソナライズなど、マーケティングオートメーションに関するレコメンドシステムを開発・運用しています。 以前、テックブログで工数やAI活用による工数削減を計測する仕組みを、タスク管理ツールのG…
AXI: Agent eXperience Interface
10 design principles for agent-ergonomic CLI. 100% task success at the lowest cost — validated across two benchmarks and 915 runs.
i18n toolkit · locallingo
AI-assisted i18n translation, source-hash drift detection, and quality linting for Rails, built on i18n-tasks and RubyLLM. Config-driven per app and package, with the lingo CLI and shipped RuboCop cops.
Ruby & Rails LLM Discoverability Scorecard
A measured scorecard of how discoverable Ruby, Rails, and the wider ecosystem's documentation is to LLMs and AI coding agents, and what the community can do to move the needle.
thecodingend/rails-starter: AI friendly rails saas starter
AI friendly rails saas starter. Contribute to thecodingend/rails-starter development by creating an account on GitHub.
Fragua — AI agent orchestrator, composed for Rails
Fragua, an AI agent orchestrator for Rails — turn an idea into a shipped app through research, plan, spec, and ship, with agents that respect the craft.
kunchenguid/treehouse: Manage worktrees without managing worktrees.
Manage worktrees without managing worktrees. Contribute to kunchenguid/treehouse development by creating an account on GitHub.
kunchenguid/firstmate: Talk to one agent. Ship with a crew.
Talk to one agent. Ship with a crew. Contribute to kunchenguid/firstmate development by creating an account on GitHub.
GitHits - Version-aware index for public open-source code and packages
GitHits gives AI coding agents a context layer for indexed code, package docs, metadata, vulnerabilities, changelogs, dependency graphs, upgrade evidence, and examples.
llmemory: memoria persistente para agentes LLM en Ruby
Descubre llmemory, la gema Ruby que resuelve la amnesia de los LLM dotando a tus agentes de memoria persistente a corto, largo plazo y cognitiva para conversaciones inteligentes.
letta-ai/letta-code: Stateful agents that are like people, with memory, identity, and the ability to learn and adapt
Stateful agents that are like people, with memory, identity, and the ability to learn and adapt - letta-ai/letta-code
alvinunreal/oh-my-opencode-slim: Lean, fine tuned Opencode multi agent suite · Mix any models · Auto delegate tasks
Lean, fine tuned Opencode multi agent suite · Mix any models · Auto delegate tasks - alvinunreal/oh-my-opencode-slim
Why LLM Benchmarks Don't Predict Great Agents at OmbuLabs Blog | Custom AI Solutions
Benchmark leaders don't always make the best agents. Explore the factors that matter most in real-world AI systems.
Giving Claude Code A Persistent Memory
Claude Code forgets everything when a session ends. I built recall to fix that — a self-improving memory layer that captures sessions, distills durable knowledge nightly, and feeds it back automatically.
zarpay/rails-template: Opinionated, agent-native Rails template — the production Rails starter ZAR uses internally, packaged with a CLAUDE.md operating manual, 32 Claude skills, and 17 path-scoped coding rules.
Opinionated, agent-native Rails template — the production Rails starter ZAR uses internally, packaged with a CLAUDE.md operating manual, 32 Claude skills, and 17 path-scoped coding rules. - zarpay/...