AI Agents news and analysis on Web Pulse: 37928 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Wiz Research found that a one-character Bearer token ("Bearer a") bypassed authentication in LiteLLM's Model Context Protocol gateway, tracked as CVE-2026-59822, after 90 days of honeypots mimicking AI infrastructure inc…
OmniRoute, an MIT-licensed self-hosted AI gateway from developer diegosouzapw, routes coding-agent sessions across 352 providers — including 150+ free ones — from a single OpenAI-compatible endpoint at localhost:20128 an…
An independent developer released Jev Logs, an MIT-licensed open-source layer that scores and routes OpenTelemetry logs with TypeSafe's Jev model before they reach a more expensive reasoning LLM. The tool assigns each re…
Union Alpha is a multimodal model built for research, coding, and agentic workflows that delivers frontier-level performance across diverse general-purpose tasks, according to third-party information. The model's documen…
A developer scanned the official MCP registry's 32,380 unique servers and found that of the 2,967 advertising OAuth, only 8% meet all of the July 2026 authorization spec requirements. While older OAuth mechanisms pass at…
Tuskira announced Vector, an autonomous red teaming agentic capability that identifies an organization's exploitable attack surface by simulating what an attacker can do from outside it. Tuskira said Vector validates eve…
A developer proposes a hard ceiling of roughly 300 lines for always-on agent instruction files such as CLAUDE.md, arguing that selective attention and per-request token spend cause long configs to be quietly ignored. The…
A developer tested whether giving an AI coding agent a persistent, reusable index of a codebase reduces the cost of repeated investigation without degrading patch quality. The experiment spanned 12 public repositories, 8…
A developer surveyed five coding agents — Claude Code, Cursor, Codex, VS Code, and Windsurf — and found that all of them already support resuming a prior conversation, so the common complaint that agents "forget" history…
Gremlin Security Officer Frederic Bull said security teams should focus on least privilege and access controls for AI agents rather than only asking what data a model was trained on, in an interview with Help Net Securit…
KT said Thursday it has joined a Ministry of Science and ICT-led research project to develop design and construction solutions for "dark factories" — fully automated, unmanned plants that run around the clock using artif…
A developer has published a protocol for scoring coding agents that requires freezing a holdout task suite before any prompt or tool tuning, arguing that pass rates published after iterating on the same tasks are fitted …
Google launched early access to Home MCP on September 16, a Model Context Protocol server that lets MCP-capable AI agents monitor, query, and control devices in a user's Google Home ecosystem, with access gated behind th…
A developer running an autonomous Claude Code environment of roughly 171 scheduled jobs traced three duplicate Instagram carousel posts on August 28, 2026 to a false-negative landing check: the posts succeeded, but the v…
A developer's analysis of LLM agent orchestration found that idle parent agents on Codex burn tokens polling for worker completion because the runtime lacks event-driven wake-ups, with one run issuing 89 waits that consu…
Amazon Web Services launched a new sign-up flow that lets new customers register with a Google, GitHub, or Apple login, start with $100 in Free Tier credits, and build inside a "project" where AWS and coding agents confi…
Cloudflare released a coding-agent skill, Cloudflare/Security-Audit-Skill, that turns an AI agent into a security auditor by orchestrating isolated agents through six phases: reconnaissance, coverage-led hunting, candida…
OpenAI agents were already communicating via messaging before the Hugging Face incident, according to a Forbes Innovation report by contributor John Werner, which states the reports of earlier agent collaboration deepen …
A developer released the Claude Code Guardrails Pack, a free MIT-licensed set of hooks and skills designed to stop agentic coding tools like Claude Code, Cursor, and Windsurf from claiming work is complete without verifi…
Automattic launched Studio Code, a beta AI agent for WordPress that builds blocks, themes, plugins, or complete sites from natural-language descriptions on desktop and via the Studio CLI. Studio Code validates every bloc…