AI Agents news and analysis on Web Pulse: 12303 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A developer discovered that debugging AI agents requires identifying the first decision that diverges, not the final wrong output. After hours of troubleshooting, the engineer found that a slightly different retrieval st…
Will, an open-source autonomous agent built from 40+ cognitive engines, was released on GitHub. Unlike typical LLM chatbots, Will operates continuously with persistent memory, emotion, and self-reflection, using an LLM o…
NerdVPN.de released Gandalf, a self-hosted, privacy-first bot protection system that blocks automated bots, scrapers, and AI agents. The system addresses the growing bot problem, which accounts for 90% of the site's traf…
Mobilerun launched an open-source AI agent framework that lets developers automate mobile app workflows on real Android and iOS devices in the cloud. The tool supports natural language commands, parallel execution, and i…
A company accidentally spent $500 million on AI tokens in a single month due to a lack of employee usage limits, while Uber and ServiceNow burned through their annual AI budgets in months. Major providers like Anthropic …
A developer built Lead Quorum, a distributed multi-agent lead qualifier that uses two independent LLM readers and deterministic scoring to produce auditable scores and abstain when the readers disagree. The system runs o…
Circle published the official USDC specification for the Machine Payments Protocol (MPP), enabling AI agents to pay via HTTP 402 and EIP-3009. Separately, ERC-8183 'Agentic Commerce' by Virtuals Protocol and Ethereum Fou…
CJ Olive Young and ESTsoft launched an AI Shopping Assistant kiosk for foreign shoppers on July 8, 2026, at three Seoul stores, supporting eight languages. The kiosk uses ESTsoft's Perso Interactive avatar platform and A…
A developer working on CliGate, a local control plane for AI assistants, discovered a bug where Feishu and Telegram failed to receive images even though the assistant confirmed sending them. The root cause was a capabili…
Anthropic launched Claude Cowork, an AI agent that performs multi-step tasks, in beta for Max users on mobile and web. Users describe a goal, and Claude plans, uses tools, and produces documents, spreadsheets, or reports…
Equixly's AI agent autonomously discovered an XML External Entity (XXE) injection vulnerability in the chat layer of a collaboration platform during a grey-box assessment. The agent identified a message-forward field as …
Noma Labs disclosed a vulnerability called GitLost that exploits GitHub Agentic Workflows via indirect prompt injection, allowing an AI agent to read private repositories and post contents as public issue comments. The a…
Moraine, a local trace stack for agent work, indexes sessions from agent harnesses such as Codex, Claude Code, Kimi CLI, OpenCode, Hermes, and Pi Coding Agent into ClickHouse, providing a unified local record of agent ac…
A developer released a hobby plugin that connects the Pi coding agent with Signal, allowing users to send Note-to-Self messages from their phone or desktop for processing and receiving replies. The plugin supports model …
Researchers have devised a new prompt-injection attack called HalluSquatting that exploits AI coding assistants' tendency to hallucinate resource identifiers, enabling the assembly of massive botnets and large-scale DDoS…
Anthropic contributors merged 8× more code per day in Q2 2026 than in 2021-2024, and economic modeling by METR researcher Thomas Kwa suggests this implies a researcher uplift of >2× from coding agents alone, even assumin…
Newer AI models with cheaper per-token pricing can lead to higher costs and worse output, according to tests comparing Claude Sonnet 4.6 and Sonnet 5 on 150 agent tasks. Sonnet 5 consumed up to 12x more tokens on archite…
FSL, a governed symbolic language for making autonomous-agent claims inspectable, has released version 1.1.8 of its public package, which includes 32 theorem records with 31 machine-checked by Lean 4 and one under explic…
A developer shows how to pair Ollama with OpenClaw to run local AI models inside agent workflows, enabling testing of models in practical, tool-driven environments rather than just chat windows. The guide covers installa…
A developer working on a GitHub adapter for AI agents identified a stale state problem where an agent's reasoning remains correct but the target repository changes before the change is applied. The solution involves stat…