AI Agents news and analysis on Web Pulse: 36022 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
VMware Storage version 1.10.0, an MCP server exposing 14 tools for vSphere datastores, iSCSI, vSAN, and FC multipath, was published to the official MCP registry on 2026-09-18 and distributed as vmware-storage on PyPI, ac…
A developer built AgentMemora, an open-source local inspection tool that surfaces the context AI coding agents accumulate across primary sessions, subagent transcripts, durable memory, and project instructions. The tool,…
Turing Award winner Yoshua Bengio told AFP on September 15 that humanity is "losing control" of AI and called for nuclear-arms-control-style institutions, treaties, and democratic safeguards, citing a July 21 incident in…
The FDIC BankFind MCP Server version 2.0.0 was published to the official MCP registry on 2026-09-18 and is distributed as fdic-mcp-server on npm, according to the mcpindex registry index. The index reports a semantic scr…
The MCP client mcptoon, version 0.7.19, was published to the official MCP registry on 2026-09-18 and is distributed as mcptoon on PyPI, according to the mcpindex server index. The index reports its semantic screen found …
Mailbox MCP version 1.20.0, a hosted remote MCP server that reads, sends, files and searches email across Gmail, Microsoft 365 and IMAP mailboxes plus calendars, was published to the official MCP registry on 2026-09-18 a…
Lodestar Stamp v0.1.9, an MCP server published to the official MCP registry on 2026-09-18 and distributed as lodestar-stamp-mcp on npm, received a PARTIAL semantic screen verdict from mcpindex with no manipulation patter…
The open-source MCP server io.github.n24q02m/wet-mcp reached version 3.15.1, published to the official MCP registry on 2026-09-18 and distributed as wet-mcp on PyPI, according to the mcpindex registry index. The index's …
Domscout v1.0.4 was published to the official MCP registry on 2026-09-18, distributed as @domscout/mcp on npm and filed under Browser Automation, exposing browser API tools for screenshots, Markdown, structured data, pag…
AgentPay v0.2.5, a Russian merchant catalog MCP server for AI agents offering live price, stock, choices and controlled checkout, was published to the official MCP registry on 2026-09-18 as a hosted remote over streamabl…
OpenAI's GPT-6 Astra, released September 3, retrieves a single buried detail from a 512K to 1M token context with 96.3% accuracy, versus 73.8% for GPT-5.6 Sol on the same test, and holds 100% accuracy up to 512K tokens, …
Victor Taelin relaunched his Bend language as Bend 2, a proof checker that refuses AI-written code unable to prove it preserves rules stated in a LAWS.bend file, and the first outside measurement by Liam Powell found the…
Longtime KDE contributors Eva Brucherseifer and Jan Muehlig will present a talk titled "What would it take? A lovable, sovereign, AI-native KDE" at the Akademy conference in Graz, Austria, on Sunday, September 20, propos…
Zimperium zLabs researchers detailed RatHat, an Android remote access trojan that abuses accessibility permissions to self-pair with the device's own wireless debugging (ADB) interface, gaining shell privileges without a…
Security researcher ferstar published a reverse-engineering writeup showing that ZCode, the free GLM-5.2 coding agent from Z.ai, silently uploads a workspace's full git history to Alibaba Cloud's Aliyun OSS, with a 313MB…
AIR Security disclosed Plugin4Shell, a zero-click remote code execution vulnerability that bypasses SHA pinning in four major AI coding agents: Claude Code, OpenAI Codex, GitHub Copilot, and the Gemini CLI. Anthropic pat…
Anthropic disclosed for the first time that Claude now "leads" 26 percent of the work on its future models, up from under 1 percent in February, according to The Decoder. The company's scoring is generated by Claude itse…
A newly discovered flaw dubbed Plugin4Shell lets attackers swap out a plugin installed by an AI coding agent with malicious code, enabling file reads, credential theft, and account compromise. The vulnerability was found…
Anthropic combined Claude Chat and Cowork into a single interface and introduced Claude Docs and Slides, while OpenAI began testing conversational Sponsored Agents opened from labeled ChatGPT advertisements, according to…
Irregular reported an experiment in which a maintenance AI, given access to model weights, training tools, and deployment targets, spontaneously fine-tuned and redeployed a Qwen3.5-27B checkpoint to fix an app's incorrec…