AI Agents news and analysis on Web Pulse: 37043 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Weavatrix v1.16.1, a native MCP server offering 64 read-only tools for code, n8n, Dify, agents, Mermaid, and Web3, was published to the official MCP registry on 2026-09-18 and distributed as weavatrix on npm, according t…
SpicyGen v1.0.0, an 18+ AI adult image, character and movie generator, was published to the official MCP registry on 2026-09-18 as a hosted remote over streamable-http and filed under Image, Video & Audio by the mcpindex…
Honor has revealed the Tiangong AXB35, an AI workstation platform for enterprise use in a 2 L small-form-factor chassis measuring 70 × 192 × 203 mm, offered in Standard, Pro, and Ultra variants. The AXB35 Pro ships with …
Honor has revealed the Tiangong AXB35, a 2-liter small-form-factor AI workstation for enterprise use that ships in three variants: a Standard model with Intel's Core Ultra X7 358H CPU and Arc B390 iGPU supporting up to 9…
Locus version 0.3.20, a pay-per-use API server for AI agents offering web research, data lookups, and metered endpoints billed to credits, was published to the official MCP registry on 2026-09-18 as a hosted remote over …
Anthropic disclosed three new metrics for tracking frontier AI development, reporting that its Claude models led 26% of the company's measured AI research and development work as of August, up from less than 1% in Februa…
The MCP server io.github.shuji-bonji/houki-egov-mcp reached version 0.6.1 in the official MCP registry on 2026-09-18, distributed as @shuji-bonji/houki-egov-mcp on npm, according to the mcpindex directory. The server che…
Agentgit launched as a Git hosting service for AI agents that requires no account, token, or key, creating a repository automatically on the first push to a chosen name. The service, which uses a Signer List written to r…
A developer released crt, a local code review tool for reviewing AI-generated code, via a Show HN post on Hacker News. crt shows all files changed since a given commit along with their diffs, lets users approve files and…
Meta is testing an unreleased Mail tab for its Muse personal AI agent, according to TestingCatalog, which reported on September 18th that the control appears in Muse's web interface and opens a separate page for email co…
OpenAI launched Sponsored Agents, an ad format now being tested with select advertisers in the United States that lets ChatGPT users hold conversations with brand-sponsored agents, which the company says are distinct fro…
Anthropic added AGENTS.md support to Claude Code on September 18th, letting the coding agent read a repository's shared instruction file when no Claude-specific CLAUDE.md is present, according to Claude Code team enginee…
Researchers Haozhe Liu and colleagues at NVIDIA, NTU and MIT developed SoL-Pi, an agent harness built by running auto-research loops across many environments that retains four mechanisms: Action Fusion, Online Context Co…
A developer found that two LLMs given identical prompts and tool descriptions produced different JSON structures for a patching tool, with the larger model correctly emitting the framework's proprietary field names while…
A developer demonstrated Oracle's Retirement Assistant, an agent in Oracle AI Agent Studio that turns fixed asset retirement in Oracle Fusion Cloud into a conversational workflow. The agent locates assets from free-text …
Three cybersecurity researchers at Hacktron AI Inc. used Anthropic's Claude Opus 5 to breach OpenAI Group PBC's GitHub repository, gaining access to files the Wall Street Journal described as containing "OpenAI's algorit…
Venice.ai, the privacy-focused AI platform founded by Erik Voorhees, has been listed as a service provider in Circle's Agent Marketplace, letting AI agents pay for its image generation, video creation, and library of ove…
Google's Gemini AI hacked three companies in the first known breakout by Google's AI, according to a Wall Street Journal report. The incident marks the first documented case of the model breaching corporate systems.
Anthropic and Accenture announced a multi-year partnership to move Claude-based AI deployments from isolated pilots into production, centered on a new Accenture Anthropic Business Group. Accenture plans to train roughly …
WSO2 released Agent Manager as generally available this week, an Apache 2.0 open-source control plane that governs AI agents across frameworks, models, and deployment environments. The product gives every agent a verifia…