Spens, a Show HN project, launched agent sandboxing that runs coding agents in isolated Docker containers and logs every network call, tool invocation, and file change for review in a local web viewer…
OpenHand released Sidekick, an AI agent that joins telehealth appointments on macOS and Windows to explain medical terminology, suggest questions, and compile visit summaries and next steps. The tool …
President Trump signed an executive order officially rebranding artificial intelligence as "super intelligence" and convened major tech CEOs—including Mark Zuckerberg, Jeff Bezos, Elon Musk, and Anthr…
Keel launched a domain-specific typed strategy language that lets developers represent, test, and deploy AI trading strategies without granting language models direct execution access to accounts, acc…
Innerloop released Breadcrumb, a macOS tool that records local screen activity and meeting transcripts to give AI coding assistants persistent context about a user's machine and calendar. Breadcrumb a…
A developer released Perspica, a semantic diff tool hosted on GitHub and shared via Show HN, to help developers review large pull requests generated by coding agents. The creator said the tool was bui…
Apple announced new controls on macOS Full Disk Access permissions, citing risks from increasingly capable AI agents that can reach users' files, messages, mail, and browsing history, according to Tec…
Google announced Gemini 4 Argon, a frontier model built for complex software engineering, legal and finance analysis, and cybersecurity defense, with access restricted to a limited set of "trusted cyb…
Groundtrack launched a platform that lets coding agents continuously improve by capturing review corrections, failed approaches, and constraints from individual agent sessions across an organization, …
AilaFlow released an open-source AI workflow automation platform on GitHub that emphasizes human-AI interface design for collaborative automation workflows in team environments. The project has appear…
Cortex Apps released Engrams, an open-source framework for autonomous agent orchestration, according to a GitHub repository, positioning it as an alternative to Cognition's proprietary Devin coding ag…
Glow Security found more than 13,000 publicly accessible images exposing corporate development work after AI models inadvertently posted sensitive internal screenshots from technology companies across…
Archipelo launched Salmon, an Execution Verification Infrastructure (EVI) system that uses cryptographic protocols to make AI agent execution history verifiable, establishing verifiable execution hist…
OpenAI announced Space and Pages at its September 29 Dev Day, adding collaborative workplace software features to ChatGPT. Space is a shared workspace where coworkers collaborate with ChatGPT and Dots…
Developers released two tools aimed at improving the reliability of autonomous AI coding agents, according to GitHub and related developer releases. Relay adds recovery and verification harness patter…
An open-source CLI tool named onesie, published on GitHub, lets System One models (Jev) run inside Unix-style shell pipelines and scripts for agentic workflows. The tooling is designed to put frontier…
Meta announced an enterprise AI platform comprising the Muse consumer AI agent, Meta Business Agent, Muse API, and Muse Code, and hired the former MongoDB CEO to lead the new business division, accord…
A single operator used three open-source AI tools — Strix for vulnerability scanning, Cairn for autonomous exploitation, and Hermes for campaign orchestration — to target 105 online retailers between …
OpenAI's Codex suffered a full outage in which users received 'Incorrect API Key' errors despite holding valid credentials, according to OpenAI's status page, and the incident was resolved after mitig…
Andreessen Horowitz (a16z) published security guidance for AI agents deployed to production systems without continuous human oversight or monitoring, according to the venture firm. A16z framed the gui…