Watching teams adopt AI, I keep seeing the same 4 steps. I mapped them out here: Steps of AI Adoption

Abstract Agent-driven end-to-end (E2E) tests add a new exploratory layer to testing, but should they replace traditional deterministic tests? We ran more than 200 agentic E2E workflows using the Playwright MCP, Playwright CLI, and agent-generated Playwright tests in test workspaces using non-production data to find out how agentic testing could fit into both our and…

Give agents an operating system as a library. Runs in your existing backend – no sandboxes, VMs, or SaaS. Powered by WebAssembly & V8 isolates. - rivet-dev/agentos

A virtual operating system for agents, with filesystem, execution, and orchestration in one lightweight library.

A terminal-based coding agent

AI agent skills created by me: Dan McAteer. Contribute to DannyMac180/skills development by creating an account on GitHub.

(Tried xhigh but that negates perf wins, didn't make a noticable difference in review evals)

ClaudeとObsidianを使って「第二の脳」を作る、という話を読んだ。 （これ↓） https://x.com/chizevsm5/status/2079513704870142428 ふーん。 まず最初にいっておくと、便利なんだろうとは思う。 自分が読んだ文章だの、仕事で調べたことだの、…

Build your own coding agent with Pi Extension API. Contribute to piex-dev/piex development by creating an account on GitHub.

A deep dive into Pi’s Extension API: loader, runner, wrapper, and three event-dispatch modes.

Core capabilities from top coding agents, packaged as npm packages for on-demand install into Pi.

Lazy tmux it is a fast session manager and saver for tmux. You can save all your session and lazy restore it. - alchemmist/lazy-tmux

lazy-tmux restores only the sessions you need, preserves scrollback history, and works instantly.

Does "rtk" reduce Claude Code token usage? Part 2 of a series where we take public “token saving” add-ons for coding agents and run the same paired A/B benchmark against each of them. Part 1 was th

A paired A/B benchmark of the token-compression skill Caveman on Claude Code, run on SkillsBench: does it actually save tokens, and does it degrade AI agent output quality? Advertised saving: 65%.

Pi Workspace is a local desktop app for working with Pi across Git repositories and long-running goals. Plan, implement, and pick up where you left off. - pi-workspace/pi-workspace

Monitor AI coding agents (Claude Code, Codex, OpenCode, Pi) in your tmux panes — sidebar + status-line segment - snirt/tmux-agents-mon

See at a glance which tmux sessions have Claude/Codex working vs idle - samleeney/tmux-agent-status

How to write a Claude Code skill that automates tech debt audits for Rails applications, combining security, dependencies, coverage, and complexity.

DoorDash's AI code reviewer uses a precision-focused, multi-stage architecture to deliver trusted and actionable feedback that engineers act on.

What if every PM had a fast, context-rich first-pass reviewer before a PRD reached the review room? We built an AI PRD Evaluator at Uber to surface blind spots early, uncover prior artifacts, and give product reviews higher signal.

こんにちは。タイムリープ株式会社でエンジニアをやっております id:moznion です。 タイムリープには有史以来、データベースmigration機構が無いままに運用されているサーバーサイドアプリケーションがあり、エンジニアが気を付けてDDLを手で発行するという運用が為されていました。もちろんここには、 実際のデータ…

Come test the early stages with us.

A collection of high-performance JavaScript tools written in Rust

Self-hosted deployment platform. Contribute to oblien/openship development by creating an account on GitHub.

Open source, self-hostable deployment platform with AI-powered builds and instant rollbacks.

A visual walkthrough of what happens inside AI coding tools, built up layer by layer from a basic prompt to a full agent loop.

A comprehensive comparison of modern frontend frameworks

A semantic code bookmarking system for humans and agents - DanielCardonaRojas/codemark

Give Devin the ability to run on any machine.