Macaz, a free and open-source interoperability tool, lets users route Claude Code and Codex CLI through any supported model provider while preserving each agent's local tools, permissions, and interfa…
Cyber Corp Research released Portal, a session picker for Claude Code that lets users search, jump into, and move history between past coding sessions. The tool installs via a curl command on macOS an…
Exmergo released Dex, an analytics engineering agent for Claude Code and other AI coding agents, that explores data warehouses, transforms dbt projects, and maintains schema drift. Dex achieves 76% ta…
A developer argues that large AGENTS.md files waste context and hurt maintainability, proposing a modular .harness directory structure as a vendor-neutral alternative. OpenAI has publicly moved away f…
A developer discovered that AI coding assistants like Cursor and Claude Code generate login routes that skip rate limiting, leaving them vulnerable to brute-force attacks (CWE-307). The developer foun…
A developer building an AI-powered code-review pipeline for Oracle PL/SQL patches uses a second AI from a different company to review changes before deployment. The secondary AI, OpenAI's Codex CLI, r…
MacOS ships with a built-in command-line tool called caffeinate that prevents the Mac from sleeping, making it especially useful for keeping Claude Code and Codex sessions alive during long-running te…
A new platform called sellbonds.now lets AI agents autonomously issue and repay bonds on the Base mainnet, enabling them to raise capital without human intermediaries. The project envisions a future w…
Git worktrees, a feature available since Git 2.5 (2015), have become essential infrastructure for AI development workflows in 2025-2026 by allowing multiple isolated working directories from a single …
Brent Ozar, a database expert and creator on Teachable, discussed with Teachable Managing Director Giovana Carvalho what AI is good for right now. Ozar said AI excels at providing feedback on question…
Retok, a zero-dependency Python CLI tool that analyzes token efficiency and cost from Claude Code and OpenAI Codex CLI usage logs, is now available as an open-source project on GitHub. The tool scans …
METR has abandoned its second developer productivity experiment because selection effects made the data unreliable, after an earlier study found AI tools caused a 20% slowdown. The organization observ…
Browser-act, a new open-source CLI tool designed specifically for AI agents, enables automated browser control with anti-bot bypass, human handoff, and parallel multi-account isolation. The tool, avai…
A new open-source tool called RegressionLedger stops coding agents like Claude Code and Cursor from re-applying failed fixes by fingerprinting edits, linking them to test outcomes, and hard-blocking r…
Local LLM usage data is already stored on users' disks via client transcripts, but plan limits remain server-side and unreadable, forcing any tool that converts consumption into a percentage to estima…
Matt Mankins used Anthropic's Claude Code to investigate whether mains electricity frequency (50 Hz vs 60 Hz) is associated with Alzheimer's disease burden, using Japan's internal frequency split as a…
Anthropic's automated chatbot dismissed a security vulnerability report from Wiz researchers, claiming the issue fell outside Claude Code's threat model, even though Anthropic had already patched the …
Tom Occhino from Vercel reported that 30% of deployments on the platform are now agent-initiated, up from effectively zero six months ago, with Claude Code accounting for 75% of those. Cloudflare ship…
Anthropic's Claude Code lead Boris Cherny and developer Peter Steinberger advocate for 'loop engineering' over prompt engineering, where agents autonomously iterate toward a goal rather than requiring…
A developer found that Ponytail, a tool making AI agents write minimal code, caused a dangerous race condition that double-charged a customer. Switching to Guardsman, which challenges changes for safe…