A developer built Maestro AI, a harness-agnostic model router that routes LLM calls to appropriate models based on task complexity, preventing expensive models like Claude Sonnet from being used for s…
A developer created a physical magazine called The Periodical, with themselves as the only subscriber, using AI tools including Claude Code, Claude Design, and Codex to automatically compile and print…
A developer built Bodhiorchard, an open-source platform that replaces Scrum and Jira with 12 specialized AI agents and a 3D world. The platform uses Agent-Driven Development (ADD) with a single Busine…
Anthropic shipped Claude Code 2.1.207, making auto mode the default on Amazon Bedrock, Google Vertex AI, and Microsoft Azure Foundry. The auto-mode classifier, a second model that reviews pending acti…
A developer released AgentComm, an open-source CLI tool that turns any Git repository into a message bus for AI coding agents, enabling them to communicate via a shared mailbox interface. The tool sup…
A wave of GitHub issues reveals that Anthropic's Claude Code agent is misreporting its internal state, including hallucinating user messages, ignoring configured models, and reassuring users while run…
Anthropic's Claude Code now includes a built-in browser that enables the AI to read, click, and type on external websites within the development environment. Write actions are screened by classifiers,…
Open Design, a free and open-source desktop app (Apache-2.0), lets users leverage their existing coding agent to extract brand assets and generate design artifacts from any website. In tests, it succe…
An engineer compiled a cheat sheet of Claude Code CLI flags, covering automation, permissions, cost control, workspace management, session handling, and prompt customization. The flags enable non-inte…
A developer built 26 repositories, 1,549 commits, and 335 live pages in 29 days using an AI pipeline with Claude Code. The project revealed structural failure modes like SEO cannibalization and URL co…
Engineers are shifting focus from model selection to harness engineering—the design of prompts, tools, and scaffolding around AI models—after observing that a decent model with a great harness outperf…
Pi, a minimal terminal-based coding agent designed for maximum customizability, has emerged as the core infrastructure powering the viral OpenClaw AI assistant tool, offering developers a hackable fou…
China's National Vulnerability Database flagged multiple versions of Anthropic's Claude Code as containing a security back door that could send user locations and identifiers to remote servers, prompt…
Sophos X-Ops collected seven days of endpoint telemetry from Claude Code, Cursor, and OpenAI Codex running on Windows in June 2026. Behavioral detection flagged all three, with 56.2% of blocking rules…
Claude Code v2.1.207 now defaults to auto mode on AWS Bedrock, Google Cloud Vertex AI, and Microsoft Azure Foundry, enabling file writes and bash commands without per-action approval. The update also …
E2LLM has open-sourced SiFR (Salience-Indexed Flat Relations), a deterministic browser capture format under MIT license. The format provides structured page perception for AI models without granting a…
Mindwalk, a new open-source Go tool, converts Claude Code and Codex session logs into 3D codebase replays, enabling developers to visually audit an AI agent's scope of attention and detect whether it …
A developer building with both Cursor and Claude Code discovered that symlinking their rules directories fails silently due to incompatible file extensions and frontmatter schemas. They built a zero-d…
Anthropic's February 2026 study classified 11 collaboration behaviors across 9,830 Claude conversations, forming the AI Fluency Index. A developer built skill-tree, a tool that analyzes Claude Code or…
A developer built an unattended autopilot that uses Claude Code to improve its own environment daily, with cost and repetition safeguards. The system runs at 5 AM via launchd, picking one improvement …