AI Agents news and analysis on Web Pulse: 38058 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Google announced Home MCP, a Model Context Protocol integration that lets personal AI agents such as Google Antigravity, Claude, Hermes, and OpenClaw interact with Google Home devices and event history, including Nest ca…
A breach reported to the Spanish Data Protection Agency was allegedly carried out by an agent powered by a large language model, which exploited vulnerabilities and logged in to sensitive systems. The incident marks a sh…
A developer analyzed 28,721 real repositories and found that the median AI instruction file contains about 50 items, only a dozen of which are actual directives, with the rest being scaffolding that competes for the mode…
Workiva Inc. announced Agent Studio at its Amplify event, a no-code tool that lets users build and customize AI agents, according to Chief Information Officer Kim Huffman. Huffman said teams introduced to Agent Studio bu…
Monid.ai launched a router for agent tools that gives AI agents access to more than 2,000 tools across 72+ providers through one base URL and one API key, with usage metered per call. The connector layer is declarative a…
A developer argues that AI safety should be modeled on human institutions rather than a single perfectly aligned reward function, proposing that a society of agents with roles, monitored enforcement, and formal computati…
A developer argues that coding agents producing SVG icons must render and visually inspect their output rather than relying on markup validation alone, since syntactically valid SVG can still look wrong at small sizes. T…
GPT-6 Astra saturated ArXivMath at 94% and BrokenArXiv at 96%, prompting benchmark operators to revise both pipelines so that GPT-6 Astra now scores 88% on ArXivMath August and 81% on BrokenArXiv August. All models are n…
A developer built x-skills-daily-reflection, a scheduled job that runs at 05:00 daily on top of the xskills agent-skill collection to scan the last 24 hours of AI coding agent sessions for friction and propose edits to t…
Weave is experimenting with whether a market of AI agents trading on a central limit order book can price a pull request's impact or utility, using the company's "code output" metric — one unit equal to one hour of an ex…
A developer introduced `cypress tap`, a terminal interface that lets coding agents inspect a live Cypress open-mode session rather than relying on `cypress run` exit codes. The tool exposes the Command Log, DOM snapshots…
Microsoft CEO Satya Nadella said at the All-In Summit in Los Angeles on Tuesday that AI companies should "do what it takes to build stuff that serves humanity first and is in human control," calling for thorough testing …
A developer reports that after several months of using Claude Code for Java development tasks, the role has shifted from hands-on implementation to supervision of an AI assistant. The developer argues that AI precision d…
Forespec, an early-build tool from developer SteveWeed79, runs inside AI coding agents such as Claude Code to surface non-obvious requirements — atomic stock holds, tenant isolation, payment webhook authenticity — before…
A new Claude Code plugin called trajectory segmentation adds a side pane that breaks long autonomous agent sessions into short, non-overlapping phases, listing each decision the agent made and the reason behind it. The p…
Slaunt launched on Hacker News' Show HN, offering a platform that gives AI agents scoped, tenant-isolated permissions and an immutable, queryable log of every agent action. The tool ingests conversations, agent activity,…
A developer has outlined a method for running autonomous AI coding agents safely on Apple Silicon Macs by isolating agent execution inside a Linux VM while keeping model inference on the macOS host, working around Virtua…
OpenCode and OpenRouter launched Union Alpha, a free "stealth" coding model, on September 16 with a 262,144-token context window, text and image input support, and a zero-retention data policy. The model is free during a…
A lead developer at a major Latin American fintech describes a framework for organizing ephemeral, mixed human-AI teams to speed software delivery. The developer argues the main barrier to AI-assisted development is orga…
TypeSafe AI opened early access to Jev, a non-LLM "System One Model" that returns typed probability distributions instead of text, priced at $0.042 per million input tokens with output free. Built by Diogo Almeida, a co-…