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.
Neo4j announced the Neo4j Ontology Graph Specification, an open-source specification for representing domain knowledge in machine-readable form to enable interoperability and automation across data, applications, and AI …
Headron Software, an open-source project, has released contract version 3.62, an infrastructure layer that enforces deterministic verification for AI coding agents by mapping source changes to declared checks and recordi…
Kapwing launched a Model Context Protocol (MCP) server that lets Claude Web, Claude Desktop, Claude Code, Cowork, and ChatGPT users upload footage, pull exports, generate and edit media, and subtitle, dub, and translate …
A developer built One-Step SEO, an open-source, zero-dependency Node.js CLI that audits a website's traditional SEO and Generative Engine Optimization (GEO) readiness and reports the two as separate scores. Run via npx, …
Goldman Sachs has restricted access to advanced AI coding tools such as Anthropic's Claude Code and Microsoft's GitHub to engineers and quantitative "strats," barring traders and bankers from using them, Bloomberg report…
Google's TPUv7 (Ironwood) delivered 1.42 to 1.67 times better performance per dollar than Nvidia's GB300 NVL72 on the AgentX agentic inference benchmark, according to SemiAnalysis. The TPUv7 submissions ran the 397-billi…
A developer released THX-02, a 4.5B-parameter open decision model under Apache-2.0 weights, runtime and server, with a free hosted API. The model returns calibrated probability distributions over user-supplied options (c…
Y Combinator CEO Garry Tan open-sourced gstack in March, a 23-command Claude Code skill pack that has reached 139,000 GitHub stars and that Tan credits with helping him ship three production services and over 40 features…
Oracle introduced Fusion Claw on September 29, 2026, a governed agentic execution runtime for its Fusion Cloud Applications that pairs large language models with deterministic enterprise computation so AI agents can plan…
At a Quito Lambda session on October 28, Stack Builders developer Gandhy García demonstrated an AI coding agent debugging a Python/FastAPI DynamoDB game API against a locally emulated AWS environment via LocalStack, usin…
SemiAnalysis published the first official long-context, multi-turn agentic inference benchmark results on Google's TPUv7 (Ironwood) across four models on its InferenceX/AgentX benchmark, finding the chip either competiti…
A benchmark by Arun Prabhakaran of LatentAILabs measured a 10-turn DevOps chat on Qwen/Qwen3-8B in bfloat16 on an NVIDIA A100-SXM4-40GB and found that re-prefilling the full transcript processes 5,549 tokens to read a 96…
AWS on Thursday made Kiro bots generally available within Kiro Crew, its open-source multi-agent development environment, letting developers assign bots specific responsibilities such as issue triage, build monitoring, a…
Smartsheet announced vsActual on Wednesday at its Engage event, a standalone "AI-native" application that uses AI agents to monitor company-wide strategy execution, detect budget overruns, schedule delays and resource co…
TrendForce estimates that agentic AI workloads could raise data center CPU core requirements from roughly 30 million cores per gigawatt to 120 million cores per gigawatt, a potential fourfold increase, and push the CPU-t…
An intern at RakFort testing secfoo, an open-source MIT CLI that runs AI coding agents against a fixed security brief, found that the tool's built-in agent produced three plausible vulnerability findings without ever rec…
Sakani launched Sakani UI, a component library of 130+ components and 42 blocks that the company says matches a Figma file exactly, is MIT licensed and free with no account required. The library ships with a SakaniUI MCP…
Opposable's Android agent app completed 91% of 3,324 actions across 45 Android phones between 8 October and 3 November, with 305 failures, according to the company's own activity log. Of those failures, 140 came from the…
A developer built Agent-Token-Optimizer, an open-source Python library for deterministic prompt compression and JSON pruning that reports 60% to 85% token reduction in under 0.5 milliseconds with no external dependencies…
Jahaan Suthar, a computer science student in Chennai, built Steward Crew, an open-source hackathon project on Switch that runs three AI agents across Discord and Slack alongside a non-AI "Ledger" component holding the on…