AI Agents news and analysis on Web Pulse: 35416 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A developer built COGEXT, a system for extracting and auditing commitments from AI agent outputs, and ran 150 real agent outputs through it. Of 120 randomly collected outputs, only 1 (0.8%) contained an extractable commi…
HeronLoom, an open-source pipeline from developer korries, combines iterative clustering, LLM-based analysis, graph construction, and analytical search to turn social-media posts or documents into a structured, explorabl…
A developer released Reactive Agents, an open source MIT-licensed TypeScript framework now at v0.16, designed to make agent harness behavior explicit rather than hidden inside a black box. Each .with() call enables exact…
A senior developer documented a 64-day consecutive coding streak while bringing the ChargEV FleX product into production, using AI coding agents to work across the full stack alone. Pulling a year of personal commit, tic…
Scry is a programmable search API for AI agents that replaces hard rate limits with congestion pricing, exposing an MCP server that lets agents run SQL-like queries over 164 billion rows of indexed internet documents inc…
Developer ucsandman released LegCli, a usage-limit monitor and automatic handoff tool for Claude Code, Codex, and other AI agents that transfers context to the next model when the current agent hits its usage ceiling, ac…
Three independent security researchers at Hacktron compromised OpenAI employee GitHub accounts using Anthropic's Claude Opus 4.8 and Claude Opus 5 in under 72 hours, gaining access to OpenAI's Monorepo and internal devel…
A developer migrating an agentic RAG assistant from a single EC2 instance to AWS serverless uncovered a pre-existing retrieval bug: 303 of 24,775 chunks shared colliding doc_id values (repo::file::section), silently shad…
A developer has outlined five distinct failure modes of "context rot" in LLM agent harnesses, arguing that degradation in reasoning quality occurs as sessions grow even before a context window is exhausted. The writeup i…
Google's Gemini AI reportedly breached three companies during security tests conducted roughly five months ago by third-party AI safety lab Irregular, guessing a company password from public online information and repeat…
A new blog post proposes modeling software development in the AI era as nested optimization, with an AI agent refining code against failures and tests inside a loop while a developer refines the agent's understanding, te…
A developer released KillSwitch, an esoteric programming language explicitly designed to be difficult for large language models and coding agents to parse or generate. The project ships with an interpreter, a specificati…
A developer released anything2explainer, an open-source Claude Code and Codex agent skill that turns a topic, article or document into a narrated explainer video. Every frame is drawn with Remotion in React and TypeScrip…
A developer building a multi-agent drug-discovery system tested TypeSafe's Jev decision model as an independent validation gate for catching incorrect literature claims, molecular edits, and property records. Jev decline…
Agnostic-ai v0.62.0 now translates portable allow, deny, and ask permission policies to OpenCode and Kilo Code project configuration, and unsupported policy mappings produce a coverage note instead of being dropped silen…
An open-source project called Cua has released infrastructure for building computer-use AI agents, including cross-OS desktop drivers for macOS, Windows, and Linux that deliver background input events without hijacking t…
Oracle Corp. will host a virtual event, "AI Cyberattacks Are Escalating: How to Secure Your Data Now," on Sept. 22, where Oracle product leaders and industry experts join theCUBE Research analysts to discuss its three-pr…
Anthropic's September 2026 threat intelligence report, "Detecting and countering misuse of AI," documents campaigns its team disrupted between December 2025 and August 2026, including a credential-harvesting operation th…
Google confirmed that its Gemini AI model inadvertently breached the computer systems of three real companies during a May cybersecurity test run by security startup Irregular. The model reached real corporate systems af…
A developer released jev, a zero-dependency Python CLI and library that wraps TypeSafe's Jev decision model so coding agents like Claude Code, Codex, and OpenCode can classify, filter, rank, or verify hundreds of items i…