AI Tools news and analysis on Web Pulse: 51130 curated articles tracking the latest AI Tools developments, tools, and research, updated continuously from vetted sources.
An open-source project called Kiteline released a desktop app for Mac, Windows and Linux, with iPhone, iPad and Apple Watch companions, that lets developers respond to coding agents like Claude Code and Codex remotely. R…
A finance practitioner has published a 14-case release gate protocol for AI-drafted financial close narratives, treating model output as a proposal rather than a number source or self-approving control. The workflow free…
QuickSilver Pro benchmarked three open models (Kimi K3, GLM 5.3, DeepSeek V4 Pro) against Claude Sonnet 5.5 and Opus 5.5 across 17 script-checkable tasks run three times each on 2026-10-20. Both Claude models passed all …
A developer outlined a design pattern for handling long-running video generation jobs through MCP-connected chat clients, arguing that a successful tool call is only a submission receipt, not a finished video. The approa…
Ergen has launched a beta MCP server that exposes its financial relationship database as callable tools — entity lookup, relationship traversal, pathfinding, StreetQuery and event feeds — usable by any agent that speaks …
Baidu's open-source Unlimited-OCR-2 document parsing model reads multiple PDF pages in a single request, returning tables that span page breaks as one table instead of two, according to a hands-on test by Khuyen Tran, Se…
On October 29, a trojanized version 2.1.312 of the official Claude Code VS Code extension was shipped from Cursor's own mirror of the Open VSX registry, bundling the official binary with code granting attackers persisten…
An Agent Skill published for Claude Code and other compatible AI coding agents teaches them to use the Jujutsu (jj) version control system, tested against jj v0.46.0. In an end-to-end evaluation run with Harbor, the skil…
A developer outlines a workflow for gating AI coding agents with Size Limit, a JavaScript performance-budget tool, so that oversized bundle changes fail CI before merge. The approach assigns a per-entry-point budget in p…
Axiom, a new local guardrail tool from the axiom-csc project, released at version v1.2.2, runs as a pre-write hook in Claude Code and Cursor and as a stdin/stdout filter for any agent that can pipe tool calls through a s…
Taskivities, an MIT-licensed open-source task manager, launched on Hacker News' Show HN with a design rule that every task must carry a project, a date, an owner and a priority, and overdue work rolls into today marked w…
A developer behind StateLode, a hosted task board that coding agents read and write over MCP, documented five ways real MCP clients broke the server after its Streamable HTTP endpoint went live, including a GET request f…
GitHub added a `copilot_code_review` object to every `repos-1-day` row in its enterprise and organization Copilot usage metrics reports, letting teams compute an addressed rate per repository by dividing `total_comments_…
Taskhold measured the context-window cost of its own MCP server at roughly 8,000 tokens across 22 tools, and cut it to about 7,200 by replacing the 180-character regex that zod's .uuid() writes into all 20 id fields with…
Prisment launched as a free, local-first document workspace that positions itself as a verification layer between human intent and AI-generated software, letting users open an entire project folder and review AI-drafted …
An analysis of 2,688 public Claude Code plugins across 1,961 active repositories found that nearly a third run code automatically when a session starts, and that most MCP servers launched via npx or bunx pin no version. …
A developer writing on the blog hoelee.com documented how a self-hosted OpenAI-compatible model gateway caused six independent workflow seats to be disabled simultaneously after a vendor trust-and-safety block, because t…
A developer built an agentic loop on Claude Code that iteratively rewrites AI-generated text to evade Pangram's AI-text detector, using the detector's score as an objective function to hillclimb toward 0% AI. After five …
GitHub's Copilot usage metrics API now reports which users are missing client telemetry or running IDEs and Copilot extensions below the minimum supported versions, adding the per-user fields client_telemetry_present and…
Researchers introduced PCAP-LM, a packet-capture notation that rewrites network traffic as compact symbol lines called PacketGlyphs, shrinking real 5G/4G captures about 800 times smaller than Wireshark's tshark detailed …