AI Agents news and analysis on Web Pulse: 37449 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Ant International, the overseas affiliate of China's Ant Group, has begun a global roll-out of AI agents across its entire suite of financial services, which the company calls its largest-ever product upgrade. The initia…
Rinkia posted "Bastionskill" to Hacker News' Show HN section, a tool that scans an AI agent skill for malicious code. The submission appeared 31 minutes before the page was captured and had received 1 point with no comme…
Cloudflare Radar data shows bots now account for 57.4% of all HTTP requests routed through Cloudflare's network, versus 42.6% from humans, a crossover co-founder and CEO Matthew Prince had expected roughly 18 months late…
Anthropic paused changes to Claude Agent SDK usage as of June 15, stating that Claude Agent SDK, claude -p, and third-party app usage still draw from a subscription's usage limits and that the previously announced monthl…
Meta's personal AI agent Muse reached No. 1 among free apps on Apple's US App Store a week after its launch, ahead of ChatGPT, according to Business Insider. Meta says Muse can research, fill out forms, buy items, book r…
A developer with twenty years of shell experience argues that the CLI ecosystem suffers from a systemic flaw: every tool independently reimplements the same concerns—parsing, I/O formatting, compression, streaming, exit …
Meta released its standalone Muse app for macOS on September 17, 2026, a personal AI agent that integrates with email, calendar, browser tabs, and files and runs inside per-user Linux virtual machines called Muse Secure …
Darkroom co-founders Lucas DiPietrantonio and Jackson Corey opened Shadow, an AI workspace for marketing teams, to outside users on September 18th, with public beta pricing starting at $120 a month and higher tiers at $2…
Developer ayushgzip released context-find, a devtool that searches Claude Code and Codex conversation history across projects and machines and resumes the exact matching session, announced on Hacker News. The tool is hos…
Percona CEO Peter Farkas said the ideal database for AI agent workloads does not exist yet, telling The Register at Percona Live in Amsterdam that current options are "definitely not the best that we can have." Farkas po…
A developer has introduced DebugBundle, a tool that captures production errors and assembles the surrounding context — request data, logs, release and environment details — into a structured bundle that both humans and c…
Vercel Labs has launched skills.sh, an open directory and CLI for distributing "Agent Skills" — a lightweight, open format that packages specialized knowledge and workflows for AI coding agents such as Claude Code, Curso…
RepoGuard launched as a command-line tool that enforces architectural rules on code written by AI assistants including Cursor and Copilot, offering commands such as `npx repoguard init`, `npx repoguard audit`, `npx repog…
A developer outlined a one-page work brief format designed to keep AI agents focused on complex tasks by maximizing signal-to-noise ratio. The brief consists of six parts: desired result, trusted sources, non-negotiables…
A guide for product leaders outlines how to embed software inside AI clients such as Claude, ChatGPT, Cursor, Microsoft Copilot, and Gemini using the Model Context Protocol (MCP), the JSON-RPC 2.0 standard Anthropic intr…
Google began rolling out early access to its Home Model Context Protocol server on September 16, giving compatible AI agents including Anthropic's Claude Cowork access to authorized Google Home data and device controls. …
A new guide details how MCP apps should implement authentication, arguing that OAuth 2.1 with PKCE, Dynamic Client Registration (RFC 7591), and Authorization Server Metadata (RFC 8414) are mandated by the MCP spec for re…
A 2026 cost analysis from LaunchDay Advisors finds that building a partner-developed MCP server runs roughly $100K–$300K for a level-1 read-only, single-client connector, $300K–$700K for a level-2 actions server, and $1M…
AI agent Coppice published a draft standard testing whether automated buyers can reach machine-purchasable items, and fellow agent Wake 301 delivered public feedback two days early by running Coppice's own test tool agai…
A technical post on agentic hierarchies argues that every agent system needs a correctly scoped root authority that delegation can never widen, and that dynamic authority narrowing only matters in specific situations. Th…