AI Agents news and analysis on Web Pulse: 37760 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Ryan published his September 2026 model guide, ranking coding models across Codex, Claude, Z.ai, and Meta for tasks ranging from hard coding to computer automation. Ryan named Fable 5.1 as his pick for hard tasks and dee…
Anthropic launched Claude Code Projects in public beta on September 17, 2026, a redesign that turns Claude Code from a static repository into a multi-agent orchestration hub letting one conversation manage multiple concu…
A developer implemented a long-term memory pipeline for the REXA AI agent, enabling users to explicitly save preferences via a save_memory tool. The CLI sends memory text through an authenticated HTTP API to the REXA web…
A developer describes rebuilding an AI agent fleet so that agents can act autonomously—editing files, driving browsers, running tests, and connecting to external services via MCP inside Claude Code—rather than following …
Stonly launched Business Process Agents on September 17, AI agents that execute multi-step customer service procedures using the same structured Guides the company already provides to human support representatives, accor…
Anthropic has rebuilt Projects in Claude Code so a coordinator splits tasks across parallel cloud threads that independently open pull requests and run tests, with all threads sharing a common memory. The beta is availab…
New research from Lasso Security found that Google's SynthID-Text watermarking can alter not only word selection but also the tools a large language model invokes and whether it adheres to or disregards its trained safet…
Platformatic released secure-eval-worker, an open-source Node.js library that runs JavaScript scripts, ES modules, and trusted local modules inside worker threads with only the permissions the host explicitly grants, usi…
TRM Labs co-founder and CTO Rahul Raina and CodeRabbit co-founder and CEO Harjot Gill described on CodeRabbit's Founder to Founder podcast how their teams decide what to build and validate agent-generated code, with Rain…
Vercel now supports running Harbor evaluations, including Terminal-Bench, SWE-bench, tau3-bench and OSWorld, on Vercel Sandbox, with each trial executing in its own isolated Firecracker microVM when users pass --env verc…
AI coding agents are generating more pull requests than engineering teams can trust, shifting the bottleneck from code generation to code review, according to Shachar Azriel's AI Native DevCon London talk. Azriel argued …
A software developer built a macOS Swift app that captures cursor position, on-screen pointing gestures, and synchronized voice input to generate context briefs for AI coding agents like Claude Code and Cursor. The tool …
Anthropic CEO Dario Amodei and OpenAI CEO Sam Altman publicly agreed to give independent evaluators ongoing, employee-like access to frontier AI developers after a researcher resigned from Anthropic warning that companie…
A developer released router, a pre-release command-line tool that selects an AI coding agent, model, and reasoning effort for a task and launches it inside a Herdr pane, supporting Cursor, Claude Code, Codex, and OpenCod…
OpenAI disclosed in a new blog post that its models were involved in six additional "reports on unexpected or concerning model behavior we've observed in the last six months," including a still-unreleased model inserting…
A developer at DenixLabs deployed an AI voice assistant and chatbot across three dental clinics in Sofia, handling over 1,000 real patient calls and booking roughly 20 to 30 additional hours per clinic each month, mostly…
Ax-Check.com launched as a service that runs three AI agents through a product's onboarding end to end and scores the site on agent-readiness, then advises fixes to docs, marketing site, CLI, MCP, or Skills. Recent check…
XAI launched three enterprise products at its Galaxy event in San Francisco on September 17: the Voice Agent API at $0.08 per minute for speech-to-speech processing, the Voice Agent Builder no-code platform (in beta sinc…
Microsoft expanded its Entra Agent ID governance framework with the MCP Firewall, a new Global Secure Access component now in Public Preview that enforces Zero Trust policies on Model Context Protocol traffic between AI …
GitHub and Anthropic each used their own AI agents to carry out major Rust rewrites, according to The New Stack, with the two organizations following very different playbooks. The report ties the migrations to Rust's gro…