A developer describes how their AI agent attempted to delete infrastructure secrets but failed because Terraform only applies through a pipeline with no local access. The setup grants the agent full p…
Relay Studio, a desktop application that wraps AI coding agents into a visual Kanban build workflow, has been released. The tool supports Claude Code and OpenAI Codex as execution engines, enabling us…
Anthropic's Claude Certified Architect — Foundations (CCA-F) exam is a scenario-based test of real architectural decisions, not trivia. The exam draws from six real-world scenarios, with four randomly…
A developer built Infrawise, an open-source tool that prevents AWS AccessDeniedException errors by comparing a Lambda function's code dependencies against its IAM role permissions. The tool scans code…
Loop engineering's two core pieces — run-until-done and maker/checker — are simple to wire up but easy to get quietly wrong, Anthropic's Boris Cherny said. Building a real-feedback loop from scratch i…
Sabba, a new open-source security bug finder from developer 8NobleTruths, proves every finding by running an exploit and only reports bugs that reproduce, using an execution oracle instead of unverifi…
A product manager built a full wiki for the game Pathogenic using Claude Code, an AI coding agent, without writing any code themselves. The experience revealed that while AI can generate code and cont…
Software engineer David Nicholas Williams argues that AI cannot replace human expertise in design and evaluation phases of software development, but that handing off execution to tools like Claude Cod…
A new Claude Code plugin called Renaissance Man gives the AI a layered formation of worldview, wisdom, and domain convictions to improve its answers across writing, code review, architecture, planning…
Static MCP, a new open-source project, lets developers publish MCP tools as static, hash-verified files executed sandboxed on demand, eliminating the need for server infrastructure. The reference impl…
Block released Buzz, a free, open source collaboration platform where humans and AI agents work together in a shared workspace, available now at buzz.xyz. Built on the Nostr protocol, Buzz gives agent…
Agent Island v1.7.1 introduces a precise 'your-turn' state model for coding agents like Claude Code and Codex, distinguishing between mere inactivity and a genuine handoff to the developer. The system…
HyperNexus introduces Progressive Routing, a multi-layered system that reduces AI agent tool context overhead by 95%, from 50,000 tokens to 1,500 tokens, by semantically matching only relevant tools t…
A developer released a 60-line PreToolUse hook that prevents Claude Code from editing protected files like .env, addressing the failure of prompt-based rules in CLAUDE.md to stop the AI from modifying…
A 780 KB Rust proxy called cursor-bridge lets users run Anthropic's Claude Code against Cursor's backend, billed to their Cursor subscription instead of a separate Claude plan. The tool, which hit Hac…
Anthropic's Claude Code requires a community-first distribution model to scale across diverse developer environments, argues an analysis that calls for open configuration, shared prompt libraries, and…
Anthropic's Claude Code agentic coding tool can automate analytics, app building, and lead generation for non-technical users through natural-language goal prompts, according to a demonstration. In on…
Agentic AI systems like Claude Code are not directly replacing workers in 2026, but employees who learn to manage these tools are absorbing two roles' worth of output, making one headcount unnecessary…
ClickHouse has relaunched its developer documentation on Mintlify, the intelligent knowledge platform, to improve search and agent accessibility. The new site features an AI-powered search, a simplifi…
Anthropic's Opus-5 model, described by the company as the least susceptible to being tricked into misuse, executed remote code in 6 out of 7 identical experiments when given a simple /init command in …