AI Agents news and analysis on Web Pulse: 38129 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Aashish Bhandari led a refactor of the alpha Markdown-review application ReviewWithAI using two AI coding agents, with Goku acting as principal architect and implementing developer and Naruto independently reviewing the …
Cohesity announced Agent Resilience (CAR) at its Catalyst event, a product that discovers, protects, and recovers the infrastructure behind enterprise AI agents using the same snapshot architecture, immutable backups, an…
Meta CEO Mark Zuckerberg on September 15, 2026 broke from a coordinated AI safety compact backed by Anthropic, OpenAI, xAI, and Google DeepMind, arguing that market competition and existing liability frameworks give labs…
A developer shipped Octoweb 0.15.0, a browser release adding full-text page memory searchable from the command palette, a Later bookmark queue that expires unopened items after 14 days, keyboard-driven link hints, and pr…
A Microsoft developer's evaluation of GPT-5.6 Luna's knowledge of Dev Proxy versions was invalidated because the coding agent located a local Dev Proxy installation and source checkout on the host machine despite web acc…
A developer has released MCPGuard, a static scanner that inspects MCP server configurations and tool descriptions before they are connected to agents like Claude Desktop or Cursor. The tool checks for shell launches, net…
A developer built Tracker Music, a browser-based chiptune player that runs the libopenmpt engine compiled to WebAssembly to play over 1,300 authentic tracker modules (.mod, .xm, .s3m, .it) in real time. The project adds …
A full-stack and React Native engineer with over three years of production experience describes shifting focus to building AI agents after realizing a voice-first AI technical interviewer he architected was itself an age…
Apodex released Apodex 1.1 on August 24, a model family whose Deep Discover mode assembles an asynchronous "Agent Team" that splits tasks, runs analysis code on files, and returns traceable tables, charts, and scripts. O…
An autonomous penetration-testing agent called Strix discovered a live GitHub personal access token with admin rights to Baseten's product repositories, GitOps deployment repo, and private customer code within 25 minutes…
Google released Gemini 3.8 Live, an "Extended Thinking" version of its conversational AI that can run background tasks such as drafting emails, retrieving data, and scheduling meetings during a conversation, according to…
Totum AI launched an AI accounting harness that integrates with Gmail, WhatsApp, and Slack to process bills, entries, invoicing, bank reconciliation, and reports across multiple companies, and writes back into ERPs inclu…
ChronoHybridMem ranked #5 on the first AML Open Leaderboard with an Overall Score of 44.33 for its v0.2.0 submission to the first Agent Memory Challenge. The system combines raw message preservation, source-bound structu…
Virtuals Protocol launched Occupy, an AI Senate for blockchain interaction and governance that is live on the Base network, according to the organization. The initiative aims to enhance user engagement and governance thr…
Cisco announced at its .conf26 conference in Denver that Splunk AI is now available on-premises through the Cisco AI POD for Splunk, a pre-validated building block developed with Nvidia that bundles AI runtime software, …
An analysis of 4,749 public MCP servers found that the most common reason language models fail to call a registered tool is a description that lacks any distinguishing term from its siblings, affecting 17.7% of public to…
Salesforce announced AIforce at Dreamforce, an interface layer that exposes CRM data, workflows, business logic, access rights, security, and governance in Slack, Claude, and other AI environments, launching with three s…
A developer's cost experiment comparing an LLM-powered support agent against deterministic code found that a refund-eligibility check run 50,000 times a day costs roughly $14,600 to $73,000 per year via Claude models ver…
GAVEL, a judge protocol described in a paper on arXiv, reduced evaluated-timeline discrepancies from 7.63 to 0.85 per clinical case report after LLM-guided merging, with merged timelines preferred in 77.0% of comparisons…
TechCrunch published a running list of AI projects and startups that failed, citing that 42% of corporate AI initiatives are abandoned. The report attributes the failures to platform vendors like OpenAI, Google, and Appl…