OpenAI deployment chief Arnaud Fournier said in an interview that the company aims to embed AI deeply within large corporations using its own engineers, citing explosive growth of Codex and a sharp dr…
Railway has integrated Claude Code, Codex, OpenCode, and Pi into its sandbox default images, enabling users to quickly deploy agent workloads alongside existing applications and infrastructure. The sa…
Accenture is scrambling to curb non-technical workers' AI token spending on trivial tasks like PDF conversions, as leaked audio reveals soaring costs. The consulting giant's internal data shows engine…
Claude Code can improve other AI agents without training data in four of seven tested applications, performing as well as with data. Data helps only where Claude Code's prior knowledge of the task run…
Noah Lindner and the team at Bevyl launched Stupify, an anti-slop code review tool for AI agents that judges code against a user-defined taste corpus, running on OpenAI's Codex via exe.dev. The tool a…
Flounder, an autonomous white-hat security auditor, was released on Show HN. It turns coding agents into an end-to-end security audit system that prepares targets, maps attack surfaces, constructs exp…
Augment launched Cosmos, a unified cloud agents platform for AI-native engineering teams, addressing the coordination and trust challenges that arise when multiple agents generate code across a team. …
Microsoft released an open-source dependency manager for AI agents called Agent Package Manager (APM), which allows developers to declare agentic dependencies in a manifest file and reproduce them acr…
RainBreak App Mac launches a free macOS menu-bar app that enforces short, non-skippable rain-themed breaks to help AI workers rest while their agents continue running. The app cites research showing b…
Cisco released AI Defense Skill Scanner, a best-effort security scanner for AI agent skills that detects prompt injection, data exfiltration, and malicious code patterns using multi-engine detection i…
Software competition is shifting from user interfaces to agent interfaces, with platforms winning by minimizing friction for AI agents. Coding agents like Lovable and Claude Code are making prototypin…
Age of Agents, a new open-source tool from Agents Mill, visualizes AI coding agent sessions as a real-time strategy game, turning each session into a settler in a pixel-art realm. The tool runs locall…
A Hacker News user asks how to test AI-generated code, noting that current AI agents struggle with browser tests from the user's perspective and that manual testing is often cheaper and faster. The us…
Sakana AI launched Fugu, a multi-agent system delivered as a single model that dynamically orchestrates frontier models to tackle complex multi-step tasks. The system is accessible via the Sakana API …
Cato Networks joined OpenAI's Daybreak Cyber Partner Program on June 22, 2026, integrating GPT-5.5 and Codex security tools into its SASE platform to reduce vulnerability response times. The partnersh…
ClickHouse announced the Managed ClickStack MCP Server for ClickHouse Cloud, enabling AI agents to access specialized observability tools for logs, metrics, and traces. The server provides higher-leve…
A developer implements a system where Claude Code writes code diffs and a separate Codex model reviews them before human approval, using cross-model disagreement to catch bugs that self-review misses.…
Vercel's eve agent framework enables developers to deploy AI agents as separate repositories, each with a single responsibility. The author built three bots—content, ops, and growth—deployed to Vercel…
OpenAI released Plant Talk, an open-source project that lets users converse with a houseplant via ChatGPT using a webcam, microphone, and the OpenAI API. The system can optionally integrate Arduino se…
Hiring across Europe is down 25% from pandemic-era highs and 15% year over year, while U.S. hiring remains 24% below pre-pandemic levels, according to LinkedIn data. Executives at VivaTech said employ…