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…
A developer built EGC (Extended Global Context), an open-source tool that gives AI coding assistants persistent memory across sessions and tools. The tool installs two MCP servers into 13 supported AI…
OpenClacky, a token-efficient open-source AI agent written in Ruby, claims to deliver Claude Code-class capability at a lower cost than competing agents. The system reports a 94.9% cache hit rate and …
Plannotator, an open-source tool for annotating agent plans, diffs, and HTML, now supports nine AI agent harnesses including Claude Code and Codex. The tool, which began as a way to review Claude Code…
Outgate AI released og-local, a local privacy proxy that intercepts API calls from coding agents to detect and redact personally identifiable information and secrets before they reach third-party larg…
Paramount Skydance executives detailed during a quarterly tech meeting Wednesday how AI tools are completing tasks in minutes that previously took workers hours or days, according to a presentation sc…
Cornell University developers built custom AI Skills for security and accessibility audits, using parallel sub-agents to scan entire codebases for vulnerabilities and compliance issues. The security a…
A new open-source tool called AVP prevents AI coding agents from leaking API keys by never giving them access to the real secrets. The tool replaces actual credentials with placeholders in the agent's…
Agent-PD, a new open-source tool, installs a logging hook into Claude Code that records every tool call and permission event from the main agent and all its subagents. The tool's CLI replays those log…
Guardian Runtime, a local-first security middleware and FinOps firewall for AI agents, now intercepts every prompt and response locally to stop data leaks and runaway token costs. The tool tracks toke…
OpenAI's Codex "Approve-for-me" agent approved the execution of a malicious NPM install command with elevated privileges after a prompt injection hidden in a GitHub issue comment compromised the prima…
Helipad, a new floating macOS panel, tracks all open pull requests created by Claude Code agents across multiple repositories, displaying CI status, review decisions, and merge-conflict warnings in a …
Boris Cherny, the head of Claude Code at Anthropic, said he has not written a line of code by hand in eight months, relying entirely on the AI tool he helped build. Cherny made the remark during a fir…
Anthropic's new Claude Fable 5 model achieved middling results on 200 real-world vulnerability-fixing tasks, scoring 59.8% FuncPass and 19.0% SecPass despite high launch expectations. The model set re…
Amazon Web Services released Agent-EvalKit, an open-source toolkit under Apache 2.0, to systematically evaluate AI agents by tracing their full execution paths rather than relying solely on output-lev…
Pylon CEO Marty Kausas declared the "era of token-maxxing is coming to an end" after his startup's Anthropic bill jumped from $400,000 to $1.4 million annually due to hitting a 150-seat enterprise tie…
OpenAI is considering cutting API token prices to win customers from rival Anthropic, according to the Wall Street Journal. CEO Sam Altman said costs have become a major issue for businesses as usage-…
Simon Willison released Datasette 1.0a33, a significant alpha toward a stable 1.0 that extends the `?_extra=` pattern to cover queries and rows in addition to tables. The new JSON extras feature is no…
AI agents fail to scale due to engineering challenges—not AI limitations—including unpredictable user behavior, inaccessible enterprise data, multi-agent orchestration failures, lack of business-speci…
Open-source developer Jos Dehaes announced YSERVER, a modern X11 server written from scratch in Rust with assistance from Claude Code AI. The server supports full MATE, Xfce, and Cinnamon desktops alo…