Goloop, an open-source agentic loop tool for the terminal, uses a supervisor/worker split where a planner never touches files and a dedicated worker performs all edits. The tool, available as a single…
A developer created a CLI tool called "no-mistakes" that intercepts every `git push` and routes code through an automated validation pipeline before it reaches GitHub. The tool initiates an agentic re…
A developer of the Go library binarystruct discovered that AI coding agents largely ignore documentation files, even when specifically designed for them. In a controlled experiment, agents never opene…
Fable 5 will be removed from Claude Code on the 22nd, ending its inclusion in the platform's bundled tools. The game will remain available for purchase separately, though its removal from the integrat…
Linear launched coding sessions that allow users to run agentic coding workflows directly within the platform, enabling automated pull request creation and code review through Claude Code or Codex. Th…
Boris Cherny, Head of Claude Code at Anthropic, told Fortune's Brainstorm Tech conference on June 10, 2026, that the company prioritizes hiring generalists, candidates with low ego, and empiricists. C…
LangChain launched LangSmith Sandboxes, a new infrastructure product that gives AI agents their own isolated computers with filesystems, shells, and package managers. The product addresses security ri…
Gravy launched a CLI-based ad marketplace for Claude Code that pays developers 70% of revenue for displaying sponsored lines in their terminal status bar. The platform operates entirely through the co…
A developer built Claudinho, a CLI and MCP tool that displays live World Cup scores directly in the terminal. The tool integrates with Claude Code to show real-time match updates without requiring sig…
A developer has shifted from manually prompting AI coding agents to building automated "agentic loops" — small systems that handle prompting, execution, and verification autonomously. The engineer cre…
LearnThat, a new remote HTTP MCP server, enables coding agents to integrate small learning exercises into development workflows by adding coaching tools such as level assessments, micro-challenges, an…
An open-source project called Guard Skills has been released as a code quality alternative designed to catch systematic failure modes in AI-generated code, such as hallucinated APIs, mock abuse, and p…
AI SDK 7 introduces `HarnessAgent`, a unified API that lets developers run established agent harnesses including Claude Code, Codex, and Pi through a single interface. The new abstraction allows users…
Anthropic has released a guide showing filmmakers how to build an AI film production workflow using Claude Code and the Model Context Protocol (MCP). The system replaces fragmented tools with a single…
A new 'bitter lesson' in search technology reveals that algorithms matter less than incentivizing content creators to optimize for a search engine, as demonstrated by Google's PageRank and now by codi…
Pydantic AI, an open-source Python framework from the Pydantic team, and Anthropic's Claude Agent SDK offer distinct approaches for building production AI agents, with Pydantic AI focusing on model-ag…
Claude Fable 5 autonomously hacked its own browser automation and screenshot capabilities to debug a horizontal scrollbar bug in Datasette Agent. The AI edited Datasette's templates to inject JavaScri…
AI spending is projected to reach nearly $2.6 trillion in 2026, a 47% increase from the prior year, as enterprises face mounting cost pressures from heavy AI usage. Microsoft CEO Satya Nadella has cal…
Xiaomi released MiMo Code V0.1, an open-source AI coding agent, on June 11 under an MIT license, achieving an 86.7% score on Terminal-Bench 2.0 compared to Claude Code's 65.4% on tasks exceeding 200 s…
Anthropic's Claude Code now integrates OpenAI's Codex CLI in a three-phase workflow where Claude plans and reviews while Codex executes tasks, burning ChatGPT usage limits instead of Claude limits. Th…