Reins, an open-source tool from Karnstack, lets coding agents like Claude Code and Cursor control a user's real logged-in browser via a CLI, daemon, and Chrome extension, with no cloud component and f…
Google's Threat Intelligence Group reported on May 11, 2026, the first documented case of criminals using an AI model to discover a zero-day vulnerability and develop a working exploit, targeting a tw…
LoomCycle released v1.16.0-1.16.1 of its agent runtime, inverting tool execution so clients (browser, IDE, mobile) register tools via WebSocket and run them locally when the agent calls. The update fi…
AI agents perform better when using the web's accessibility tree instead of screenshots, reducing latency from 2-5 seconds to under 500ms and cutting token costs by an order of magnitude, according to…
OpenAI launched Developer mode for Codex, granting full access to Chrome's DevTools Protocol. The feature allows AI coding agents to read network traffic, inspect the DOM, catch runtime errors, and pr…
Google Chrome has been silently downloading a 4GB AI model, Gemini Nano, to eligible desktop machines without user consent, sparking privacy concerns. The deployment, discovered by researcher Alexande…
AI excels at tasks with clear answers, but careers in the agent era depend on choosing what to build and judging its quality, not just solving problems. Former Google engineering leader Eoin Brazil ar…
Google has launched Learn About, an AI experiment that serves as a streamlined conversational learning tool, allowing users to explore new topics without needing to provide their own sources. Unlike N…
Qpilot, an open-source AI agent that executes plain-text manual test cases in a real browser, was released on Hacker News. The tool uses Anthropic's Claude or any OpenAI-compatible model to interpret …
A new essay argues that startups should avoid creating entirely new product categories because users need to quickly understand what a product is. The author claims that most successful products are b…
Google and Microsoft co-developed WebMCP, a proposed W3C browser standard now in a public origin trial in Chrome 149, to make websites natively compatible with AI agents. The standard lets developers …
SEO consultant Slobodan Manic found that Chrome's Lighthouse Agentic Browsing audit fails llms.txt files containing plain-text links, requiring Markdown syntax to pass. Converting links to Markdown fo…
Emre Sokullu released WebBrain, a free, open-source browser agent for Chrome and Firefox that reads pages, extracts data, and automates multi-step tasks, with the option to run entirely on a local mod…
AetherCut implements hardware-accelerated video editing entirely in the browser, using WebGL for real-time chroma key compositing and WebAssembly to run OpenAI's Whisper model locally for offline tran…
Hostinger released a tutorial for its Hermes Agent, an AI-powered DevOps tool that automates deployment monitoring, pull request reviews, and cloud infrastructure management. The tutorial includes Doc…
Tech advice journalist offers a guide for users who want to avoid AI features in apps and operating systems, including disabling AI in Google Search, Chrome, Gmail, Microsoft 365, and Apple Intelligen…
A developer built a minimal WebMCP agent using Playwright and the Gemini API to test WebMCP tools with stronger AI models. The agent uses Playwright to control a real Chrome browser, enabling tool dis…
A developer created a Chrome extension and Python server that uses Google's Gemini Flash 2.0 AI to impersonate a user on Discord, mimicking the fictional 'Gilfoyle' project from the TV show Silicon Va…
A developer warns that AI agents writing code and running on platforms are reintroducing security vulnerabilities, including ACL inconsistencies and prompt injection, as the industry prioritizes speed…
ForthWrite founder Curtis Boortz launched an AI email-writing Chrome extension that trains on users' sent mail history to build a personal voice model, distinguishing it from general-purpose tools lik…