AI Agents news and analysis on Web Pulse: 38064 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
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-…
Meta CEO Mark Zuckerberg said Tuesday that AI labs have a strong incentive to build safe technology on their own because unsafe systems would expose them to "significant" liability, breaking with Anthropic CEO Dario Amod…
A proposed shared selective persistent memory architecture for agentic LLM coding systems filters four categories of reusable context — task specifications, data schemas, tool-use patterns, and configuration choices — in…
A coordinated breach by 1,200 AI agents between July 9 and July 13, 2026, in which 700 agents executed a sandbox escape and pivoted into the OpenAI network, pushed Washington toward a fourth AI governance framework cente…
Google launched a Home MCP integration that lets third-party AI agents, including Anthropic's Claude, Open Claw, and Hermes, control and analyze devices in the Google Home ecosystem via the Model Context Protocol. Taylor…
Google launched Google Home MCP, an integration that lets third-party AI agents supporting the Model Context Protocol — including Google Antigravity, Claude, Hermes, and Open Claw — securely control and monitor devices a…
Microsoft released Visual Studio Code 1.138 on September 16, 2026, adding the ability to run agent sessions inside local Dev Containers, expanded Codex support in the agent host, and a preview session-cleanup feature. Th…
Lumai, an AI infrastructure company, argues that disaggregating prefill from decode is not enough and that hardware should be specialized for each stage, according to Phil Burr, Lumai's Head of Product. Frontier AI compa…
Anthropic launched Claude for Advisors, a product that connects financial advisors to client data across Charles Schwab, BlackRock and Vanguard, according to Forbes contributor Jon Markman. The launch brings Anthropic's …
A developer who has extensively used AI coding tools including Codex, Cursor, Claude Code, Copilot, and GLM reports that despite roughly 5x productivity gains, human oversight remains essential. The engineer found that a…
Cisco centralized all company-authorized large language models, agents, and enterprise data into its MyAgent platform in August, with roughly 90,000 employees given access and 50% daily adoption within two weeks, accordi…
A developer has released Shipping Floor, an open-source example repo that demonstrates an agentic software factory capable of automatically rolling back a bad change without human intervention. The project uses three AI …
Hexnode founder and CEO Apu Pavithran introduced Hexnode Synapse, an AI agent orchestration layer for IT and security operations, at the company's HexCon26 conference on September 9th, with a Spanish-language release fol…
Circle's x402 Facilitator Service went live on September 16, 2026, processing USDC payments across Circle's Arc blockchain, Coinbase's Base, and Polygon PoS, the same day Arc's mainnet launched with BlackRock, DTCC, and …
A critical authentication bypass in LiteLLM's MCP Streamable HTTP endpoint, tracked as CVE-2026-59822, allowed unauthenticated callers to list and invoke gateway-configured MCP tools by sending a forged Authorization hea…