Microsoft and three Chinese universities developed SkillOpt, a method that optimizes instruction documents for AI agents using principles from traditional model training. A simple Markdown file booste…
A developer argues that the current AI revolution is fundamentally different from past waves of enthusiasm, citing the convergence of large-scale labeled data, GPU computing, and deep network architec…
A developer open-sourced Bottega, an internal agent orchestration tool used to manage coding agents, after reporting that 100% of their production code has been written by agents for the past 8 months…
A developer built Filomena, a harness to run multiple Claude Code agents from one terminal, but abandoned it after six months as Claude Code's native features rendered it obsolete. The project's core …
Developer Yasyf released cc-pool, a macOS tool that predictively load-balances Claude Code sessions across multiple Claude Max/Pro subscriptions by selecting the account with the most remaining usage …
Playwright MCP is a Model Context Protocol server that exposes Playwright's browser capabilities to AI agents, enabling them to open pages, click, type, inspect accessibility snapshots, and capture sc…
A developer built a Claude Code plugin called Chrome Extension Builder for MV3 Chrome extensions, learning that validators and hooks are more effective than clever prompts for catching MV3-specific mi…
Theta_py, a Python binding for the Theta CLI, was released on Hacker News, enabling developers to programmatically manage AI agent configurations through a Pythonic API instead of CLI commands. The li…
A developer built nodestone, an open-source project context memory engine that preserves AI coding agent context across sessions. The tool captures active tasks, decisions, and architecture drift, pro…
A developer has released nodestone, a free project-level memory engine for AI-assisted development that restores context across sessions. The tool tracks decisions, tasks, and file changes, allowing u…
A developer built Tribunal, an adversarial Claude skill that reviews code diffs by pitting biased agents against each other to produce more honest feedback. The system uses per-file 'haters' that atta…
Loop engineering is emerging as a new paradigm for working with coding agents, where developers design recursive systems that autonomously prompt agents rather than writing prompts manually. Industry …
A developer released an open-source tool that converts a folder of Markdown notes from Obsidian or gbrain into a single interactive HTML knowledge map with force-directed graph, timeline, and click-to…
A developer proposes a pattern for delivering overnight agent reports to a private, end-to-end encrypted inbox using the Agent Relay CLI, which encrypts files client-side before upload. The approach a…
XAI launched the Grok Build Plugin Marketplace on Wednesday June 11, featuring 6 plugins for terminal coding, after failing to surpass Claude Code's plugin ecosystem. The move integrates 224,691-star …
Peter Steinberger, creator of OpenClaw, and Boris Cherny, creator of Claude Code at Anthropic, independently declared in June 2026 that the future of AI engineering lies in designing loops that prompt…
A developer is building AccInt, a local Work Model for agent-run work that aims to determine what an AI coding agent should learn after a failed run. The project focuses on capturing settled commitmen…
Anthropic suspended access to Claude Fable 5 and Mythos 5 four days after launch due to a US government export-control directive, not a typical outage or jailbreak. The company disabled both models fo…
A developer has built AccInt, a local work loop for AI coding agents that implements a Work Model to track context, decisions, failed attempts, and outcomes. The system uses late-interaction retrieval…
A developer turned off AI coding tools for a week and found that while output dropped initially, code quality improved and a subtle race condition was caught that AI had dismissed. The developer now u…