AI Agents news and analysis on Web Pulse: 49187 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Amazon's North America Sort Center (NASC) team built a serverless Model Context Protocol (MCP) server on Amazon Elastic Container Service (Amazon ECS) with AWS Fargate to give LLM agents a centralized, agent-agnostic gat…
Socket's Threat Research Team found that the RubyGems package strutil-core version 1.0.1 runs a 5.48 MB credential-stealing worm at install time, and Socket's AI Scanner flagged the package 70 seconds after it was publis…
The Draw Things team released Local Code, a private AI coding agent for Apple Silicon Macs that it says is the only local coding agent in the macOS App Store, with on-device models costing $0 per token and hosted models …
Amazon Web Services published Part 2 of its guide to governing AI agent access using Okta Cross App Access and Amazon Bedrock AgentCore, moving the authorization check from each Model Context Protocol server into Amazon …
TypeSafe AI released Jev and Jared Palmer released Kev within weeks of each other in 2026, two "decision models" that return typed answers with confidence scores in a single pass instead of generating text token by token…
Google Cloud made its storage-optimized Z4M machine series generally available in Google Compute Engine as both VM and bare-metal instances, targeting AI/ML training and inference workloads such as checkpointing, distrib…
Greenlight Financial resolves more than 90 percent of up to 4,000 security and risk cases each month without human intervention using Luna, an autonomous security operations center built on Amazon Bedrock AgentCore, AWS …
Taxbit built Taxbit Assist, a grounded, role-aware AI assistant embedded in its digital-asset tax and accounting compliance dashboard, on Amazon Bedrock AgentCore using the Strands Agents SDK, and more than 55 percent of…
Orchestrator.inc released agent-orchestrator v0.14.10, an Apache-2.0 licensed, self-hosted tool that coordinates multiple AI coding agents from a single Kanban board, with 14,175 GitHub stars and a last commit one hour b…
Perplexity launched Teammates, always-on AI agents that each run on their own virtual machine with a desktop and browser and work through ongoing projects independently, tracked via dedicated threads in the Perplexity ap…
AWS published a sample, sample-remote-coding-agent, that runs Claude Code as a remote agent on Amazon Bedrock AgentCore runtime, giving each coding task its own isolated session inside the customer's AWS account and retu…
A developer built a Retrieval-Augmented Generation pipeline in Go using PostgreSQL with the pgvector extension and Ollama's embeddinggemma model, storing 768-dimension document embeddings alongside tenant metadata in a s…
A developer published a paired cost-and-latency gate script, budget_gate.py, that sits after correctness tests in AI-generated C++ patch evaluations and flags when a candidate patch set becomes more expensive per accepte…
A developer published a set of four configuration changes for OpenAI Codex CLI (v0.166.0) and Claude Code (v2.1.277+) that reduce token waste and block unapproved file writes. The changes raise Codex's default command yi…
Physical Superintelligence announced on November 6 that an internal AI research system, led by PSI technical staffer David Turturean and built on a non-public Anthropic model, produced a proof of the Aaronson-Ambainis co…
Anomaly released Rune, a pre-release, MIT-licensed native GPU-rendered Rust UI framework for macOS, Windows, Linux and the web that ships its own renderer, text, layout and springs. Every Rune app can run headless, letti…
Boson AI, the Santa Clara company co-founded and led by Alex Smola, introduced Higgs Realtime Duplex on November 5th, 2026, describing it as its first full-duplex interactive omni model, built on a 45B front model. Boson…
An Ask HN thread posted November 4, 2026 by user eggbrain asking developers for their current AI agent setup drew 663 comments from 530 people, and an analysis counted on November 6, 2026 found that 424 of those commente…
Microsoft's Foundry Local now runs the Qwen3.8-27B coding model locally on consumer GPUs with 24 GB of VRAM and connects it to GitHub Copilot, using 4-bit quantization to shrink the model to roughly 18 GB. Microsoft repo…
A developer used Claude Code with Gaffa's browser-automation skills to build a working web-scraping workflow against books.toscrape.com, going from plain-language goal to discovery, a paginated scraper, CSV export and ve…