AI Agents news and analysis on Web Pulse: 49359 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A cluster of security incidents during the week of October 19 — dubbed "Black October" — included critical PHP flaws demonstrated by Wiz as unauthenticated code execution and PHP process-memory reads of passwords, tokens…
LinearB Inc. announced Agentic Studio, an offering that normalizes data from Git repositories and project tracking tools into a unified context layer that human engineers and autonomous coding agents can query in plain l…
OpenAI is merging ChatGPT's chat and Work tabs, with ChatGPT and Codex drawing usage from the same allocation pool after the change, according to TechCrunch AI. The consolidation combines the consumer chat interface and …
An open-source Model Context Protocol server called maat lets AI agents diagnose Ubuntu systems from inside a strictly confined snap with read-only permissions and no network access, while any fix must be approved by a h…
Uber has built an MCP Gateway that standardizes how AI agents discover and invoke internal services, supporting more than 800 MCP servers and 5,000 tools, the company detailed in a blog post. The architecture splits an M…
A developer built and managed a church website project entirely from a phone, combining v0 for design generation, Claude Projects for persistent research context, and Claude Code connected to GitHub Issues to assign tick…
A developer built Serviette, a FastAPI-based RAG server on top of Pathway that performs streaming incremental document ingestion, re-embedding only changed chunks instead of triggering full reindexes. In load tests of 50…
A developer ran 120 coding-agent trials across three setups using qwen3:14b and qwen3.6:35b-a3b, comparing advisory versus enforced completion checklists that require a deliverable and a verification note to exist on dis…
A developer documented how Claude Code hooks work, describing lifecycle events including PreToolUse, PostToolUse, Stop, SessionStart and PreCompact that run commands at fixed points regardless of what the model decides. …
A newly published benchmark, Taste-Bench, tested 14 models on binary decision tasks requiring them to choose between two technical paths without seeing downstream effects, with the best model, GPT-5.6 Sol, reaching 59.7%…
Developer ajnart released self-host, an Apache-2.0 Go CLI with a terminal interface that uses Docker Compose to install and run self-hosted apps, alongside an optional agent skill for coding assistants. The tool's catalo…
Abacum co-founder and CEO Julio Martinez launched Abra on November 2, an orchestrating agent that takes a plain-language planning question and routes it to one of Abacum's specialist agents — Modeler, Analyst, Reporter a…
Hewlett Packard Enterprise reported that an internal hybrid AI routing platform cut its coding-agent token costs by 30-50%, according to a company analysis conducted in October 2026. HPE routes complex planning and heavy…
Developer tomyud1 released Poinky, a free and open-source macOS app that puts a voice-driven Claude Code assistant in the Mac's notch, letting users hold Control+Option to ask questions aloud about whatever is on their s…
OpenMarkdown released a free, local-first Markdown editor built on a native Rust core that lets a user's existing coding agent read and edit the same plain .md files on disk, with the agent running in a terminal tab insi…
A developer released pgbrake 0.2.0, an MCP server that adds a Claude Code PreToolUse hook to intercept destructive database migration commands such as `prisma migrate reset --force`, `drizzle-kit push --force` and `alemb…
A developer published a read-only bash script, key_guard.sh, that checks the shape of AI API key usage before calls leave the local code path, aiming to catch abuse of stolen keys before it shows up on a provider invoice…
Wiz launched Red Agent, an AI-powered pentester that continuously validates exploitable risks and delivers them as pre-breach SOC alerts, alongside Blue Agent, an AI investigator that works with analysts to investigate a…
HelpPuff launched as a free, MIT-licensed open-source AI site chat tool that deploys entirely into a customer's own Cloudflare account, with no subscription and no hosted control plane receiving customer data. Setup is d…
Aigenos released Flow, an Apache-2.0 open-source tool that runs LLM agent workflows as deterministic steps defined in a SKILL.md file, with the model only filling typed fields while the file decides which rules apply and…