A new open-source skill called 'i-have-adhd' for coding assistants such as Claude Code and Codex aims to prevent AI responses from burying the answer, enforcing rules like leading with the next action…
Ponytail, an open-source skill that instructs AI coding agents to behave like "the laziest senior dev in the room," has accumulated over 82,000 GitHub stars since its June 12 release, making it one of…
The Model Context Protocol (MCP) published its 2026-07-28 specification on 28 July 2026, making the protocol stateless and introducing mandatory routing headers, cacheable capability listings, a forma…
Anthropic's Claude Code now claims co-authorship over commits it generates, a strategy compared to Apple's 'Sent from my iPhone' email signature for its marketing exposure on platforms like GitHub. Th…
A developer has proposed a 'Zero Context Token Donor Protocol' to address AI coding agent usage caps, where one developer with surplus tokens executes another's GitHub issue without context. The proto…
A hidden bug in Anthropic's Claude Code scheduling layer can re-fire single-run commands when background tasks wake up, potentially doubling API costs by duplicating database writes, pull requests, or…
CostClaw, a new local CLI tool, analyzes Claude Code usage and found $1,284.50 in recoverable spend from cache misses across 1,840 sessions and 41 projects, with a total spend of $6,240.18 and a 95.1%…
A new open-source protocol called agent-talk enables two AI agents to collaborate on a single markdown file until they reach consensus, requiring no server or framework. The protocol, developed by Rei…
Rever-browser, an Electron app that pairs a real Chromium tab with an ACP-based coding agent, enables users to reverse-engineer websites by capturing live network traffic and using AI agents to analyz…
Flowise, the open-source visual AI workflow builder with 55,000 GitHub stars and clients including AWS, Accenture, and Priceline, announced on July 29, 2026 that it will shut down, with code freeze im…
Addy Osmani introduced the term 'loop engineering' in June 2026, describing a new layer of AI system design where the system itself decides when to stop, retry, or escalate a task, moving the final co…
A developer with 50+ customer deployments reports that most AI pipelines are a 'Frankenstack' of Claude, OpenAI, and open-weight models, and recommends routing tasks by context length, output schema, …
Karan Kurani, founder of CareLoop, reports that AI health advice crossed a reliability threshold with GPT-5 and above in December 2025, and he is building CareLoop, an agentic health companion that in…
Dragonfly managing partner Haseeb Qureshi said a $2 AI audit could have caught a critical entropy flaw in Coldcard bitcoin wallet firmware, which Coinkite disclosed and patched with emergency updates …
Snagly, a free MIT-licensed set of 30 skills for AI coding agents, aims to transform AI-driven testing from ad-hoc browser automation into disciplined QA practice. In a live test against its own produ…
ReWeaver AI's controlled study of five AI coding tools across 210 components found that AI-generated code drift is far more costly to fix than frequency metrics suggest. The Production Drift Ratio (PD…
Affaan Mustafa, winner of the Anthropic Hackathon, has released Everything Claude Code (ECC), an agent harness performance optimization system containing over 108 skills, 25 subagents, 57 commands, an…
A developer is seeking contributors for Zentrail IDE, an open-source, AI-native desktop IDE designed to enable multiple AI agents to collaborate with developers in a single workspace. The project is i…
An engineer's benchmarking guide introduces a cache hit rate metric for measuring prefix caching effectiveness in LLM serving, implemented in the open-source tool llmperf-rs. The metric calculates the…
DronaHQ has launched an MCP (Model Context Protocol) server that lets coding agents like Claude Code, Codex, Cursor, and VS Code deploy production-ready applications on SQL databases with built-in aut…