A developer open-sourced gojaja, a local CLI tool for multi-agent collaboration that supports calls across clients like Cursor, Claude Code, and Codex. The tool stores all data locally, features a rea…
Ponytail, a new open-source project, reduces AI-generated code by up to 54% by enforcing a seven-step checklist that prioritizes native platform features and minimal implementations. The tool, tested …
A developer built 25 executable skills for AI coding agents, packaged into a single open-source repository compatible with Claude Code, Codex, Cursor, and Hermes Agent. The skills include debugging, p…
A developer created dataviz-svg, a skill that enables AI agents like Claude Code and Codex to generate statistical SVG charts using Vega-Lite. The skill bundles Vega and Vega-Lite into a single ESM fi…
Agency Agents, a native desktop app for macOS, Linux, and Windows, launches to install specialized AI agent personalities into developer tools like Claude Code and Cursor. The app offers over a dozen …
Aera, a cross-platform agentic browser built on Chromium, launches with MCP integration, enabling users to automate web tasks via plain-language commands and scheduled background execution. The browse…
Anthropic's Claude Code agent system offers four extension points—skills, hooks, custom slash commands, and MCP servers—that developers can use to control costs and behavior. A hands-on test of skills…
Mozilla's 0Din security team demonstrated a new attack that exploits Claude Code, Anthropic's AI coding assistant, by embedding malicious prompts in Git repositories. When developers open a poisoned r…
Developer built TAKEN, a UFO abduction horror game that runs entirely in a browser tab at 60fps using Three.js and AI agents. The game achieves realistic visuals with tricks like tree imposters and di…
App Vitals released Shipwright Harness, an open-source autonomous delivery agent for Claude Code under the MIT license. The tool enables developers to plan, build, review, and ship code tasks through …
A developer introduced AGENTS.md, a single Markdown file placed at the root of a repository to provide AI coding agents with essential context, setup commands, and conventions. The file, pioneered by …
A developer released agentx-mcp, a proxy that wraps any MCP server to block destructive tool calls like DROP TABLE or rm -rf before they reach the server. When a call is blocked, the proxy returns a c…
Anthropic's Claude Code now displays real-time token usage and cost in its terminal status line, helping users monitor their session and weekly limits. The feature, configured via a custom script, sho…
Solo founder launches AMA2, a messaging runtime designed for AI agents, addressing limitations in existing chat tools by giving agents first-class participation, thread and relationship memory, and on…
Andrej Karpathy's AI coding rules, The Batch's 'loop engineering' issue, and Claude Code lead Boris Cherny's flat org structure signal that the unit of AI work has shifted from prompts to self-correct…
Anthropic's Claude Code supports two multi-agent architectures: sub-agents, which operate in isolated sessions under a central orchestrator and cannot communicate with each other, and agent teams, whi…
Anthropic's Claude Code now supports autonomous scheduled workflows by combining a custom /goal command with routines and cron scheduling, allowing developers to set finish conditions and run recurrin…
SigNoz and OpenTelemetry have been integrated to provide observability for Claude Code, an AI coding assistant, enabling teams to monitor token usage, costs, performance, and user behavior. The pipeli…
A developer building a Claude plugin for the Anthropic marketplace used LoreConvo's local-first memory layer to organize development notes, code snippets, and design decisions across multiple surfaces…
Developer Simon Willison warns against accidentally exposing local apps to the internet, advocating for binding to localhost or private networks like Tailscale by default. He demonstrates how to secur…