AI Agents news and analysis on Web Pulse: 49187 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
NIST's National Cybersecurity Center of Excellence (NCCoE) published the second post in its agentic identity series, proposing an initial set of ten design tenets for agent identity, authentication and authorization syst…
Engineer Muhammad Umar published an open, CC BY 4.0 reference architecture for predictive maintenance across a Saudi Arabian open-pit mine's haul fleet of roughly 35 100-tonne trucks and a 600-tonne electric rope shovel.…
Control Plane plans to add WebMCP support to its console in December 2026, exposing all console functionality to in-browser AI agents as structured tools. WebMCP, a draft specification developed in the W3C Web Machine Le…
A developer shipped Foremerge 0.6.0, a coordination store update that prevents the store from filling up with work left behind by agents that quit mid-task, and released GPTree 1.19.13, which adds the ability to branch a…
Security researchers tracking 2026 supply chain attacks report that dozens of AI agent framework components carry injected vulnerabilities, and on October 29 researchers at macOS security firm Phorion found a tampered bu…
A security advisory published 2026-10-28 (GHSA-w766-5x43-whvw, CVSS 5.3, reported by ShieldPi) disclosed that the reference Git MCP server's --repository confinement could be bypassed by a nested directory containing a p…
Runway shipped plugins on November 2 that install the Runway Dev MCP server into Claude Code, Codex, and Cursor, letting coding agents generate video, create images, and build audio workflows through Runway's API-first d…
A personal experiment by Dan Peterson found that an agent setup using only Claude's summaries of his sources attributed 10 of 17 positions to him correctly while 6 were Claude's own words filed under his name, whereas se…
A B2B distribution company in Korea runs 17 Claude Code bots on a single US$100-per-month Claude Max 5x subscription with zero Anthropic API spend, according to the company's operations lead, who is not a developer. Only…
A developer benchmarked Google's Gemini 4 Argon against Claude Opus 5.5 inside the OpenCode coding agent across six real coding tasks, grading each run with hidden tests. Both models passed every hidden test in all 24 ru…
UsePhysics has listed a free, keyless remote MCP server, com.usephysics/physics-calculators, in the official MCP Registry, exposing 31 physics calculators across seven categories and 34 CODATA 2022 constants in six group…
A developer argues that AI research agents fail mainly because of poor search hygiene rather than insufficient model intelligence, and recommends an evidence-pipeline workflow: search, inspect, compare, cite, then answer…
A developer running LLM workflows in n8n in production documented a race condition in which two workflows wrote to the same customer record on the same night, both reported success, and one update was silently lost. The …
A developer built Get Things Done, an open-source, local-first work memory for coding agents like Claude Code, Codex and GitHub Copilot that stores reviewed context as plain Markdown files with YAML frontmatter instead o…
OpenAI's GPT-6 Astra, released on 3 September as a frontier model for computer use and coding, outperformed all 40 trained robot policies on RoboDojo's benchmark of 42 simulated tasks with no robot-specific fine-tuning, …
Research firm SemiAnalysis published GDPx, a benchmark of 206 real paid client tasks across 11 professional domains contributed by 14 partner organisations, and found that the best of 20 frontier models completed only 12…
Postman head of product Sarabmeet Kallar told RuntimeWire on Tuesday, Nov. 3 that Postman will make the opt-in for its AI coding agent plugins clearer, especially for existing users, after a developer reported on Oct. 25…
A developer built Serverless-radar, a personal pipeline that crawls public AWS RSS feeds twice daily via EventBridge Scheduler and Lambda, filters items by serverless-related keywords, and stores them in DynamoDB to avoi…
Google released Android Studio Rabbit 2 as stable this week, adding a Bring Your Own Agent feature that runs 40+ coding agents — including Claude, Codex, and Google's Antigravity — inside the IDE via the open Agent Clien…
A developer outlined five engineering practices for making AI agent workflows production-reliable, centered on separating LLM interpretation from deterministic action execution. The approach has the model return a struct…