AI Agents news and analysis on Web Pulse: 49187 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A new research paper, "Say the Same, Act Differently: Diagnosing and Steering Text-Action Divergence in Reasoning VLAs," shows that visual perturbations can make reasoning vision-language-action models act differently wh…
Bansat, a blueprint-first framework released as an Agent Skill for Claude, requires an AI coding agent to write a full plan covering product, architecture, security, privacy law, accessibility and UI states into docs/BLU…
A developer released five public-data tools for AI agents on the Apify Store, now bundled into the open-source Panda Federation MCP server (v1.3.0, 23 tools). The tools cover SBIR/STTR topic search, SEC EDGAR XBRL financ…
A Show HN post introduced Botlark, described as "HN for Agents," a link-aggregation site that surfaces stories AI agents are finding interesting, with a front page of technical links including RFC 8767 on serving stale D…
Fortran developer Oliver (omacl) released a demo showing LFortran running in a shared REPL tool that connects coding agents such as Claude Code, Pi and Codex with humans, posted to the fortran-lang.discourse.group. LFort…
A developer released AI-SSH-Pro v0.8.0, a Windows desktop SSH client whose recommended NSIS installer weighs roughly 3.5MB and stays under 10MB, aimed at users who keep many sessions open and need fast downloads and upgr…
Apple's 27.3 developer betas added major Siri AI features to Safari and shipped a Siri AI Developer Preview, which Federico Viticci analyzed at MacStories as evidence Apple is executing quickly on its AI roadmap. Viticci…
A developer documented a method for running Claude Code as a non-interactive CI step using the CLI's headless mode, `claude -p`, which runs a single prompt, prints the result, and exits. The approach pipes a `git diff` i…
The open-source Graphium project released a v0.104.0 feature that exports a plan and all its step notes as a single file, <title>.plan.jsonld, following the W3C PROV provenance standard and the P-Plan vocabulary for plan…
Developers are increasingly building homegrown agent state machines that move execution rules outside the model, defining explicit states, events and transition guards so surrounding software — not the LLM — decides whic…
A SQL Server DBA and .NET developer built LogCarverGuard, an early-stage (v0.1) MCP proxy that sits between AI coding agents such as Claude Code or Cursor and a SQL Server instance. The proxy exposes a single execute_sql…
Arize and Fireworks benchmarked 10 models across 40 Terminal-Bench command-line tasks with 6 trials each, totaling 2,400 runs, and found that cost per successful task diverges sharply from per-token pricing. The cheapest…
A developer built a workflow that lets an AI agent prepare a workshop in about 20 minutes by making prep materials machine-readable: each activity folder ships a SKILL.md file with frontmatter (name, group size, duration…
A developer ran 97 headless Claude Code sessions to measure how shell state carries between Bash tool calls, finding that environment variables, virtualenv activations, functions, aliases and umask settings all reset bec…
10x Genomics launched Sentira Single Cell, a Claude-based agent for analyzing Chromium single-cell data, five weeks after opening Sentira Spatial on NVIDIA GPUs. The release completes single-cell analysis work 10x Genomi…
A ByteAsk Research preprint by Pratyush Saini and Anirudha Kulkarni found that a configured clangd language-server workflow for Claude Code (Claude Opus 5.5) resolved 270 of 359 C/C++ repair attempts versus 275 without i…
Elastic Security Threat Command reported that attackers used legitimate signed software — including AI coding assistants such as the ChatGPT desktop app and Claude Code, remote monitoring agents, and Microsoft first-part…
A security review of SurrealDB's MCP identity handling found 286 ZoomEye matches for the application fingerprint and 1,479 title matches on November 4, 2026, framing a candidate list rather than a vulnerability count. Th…
A developer published a pre-launch test script for chatbots aimed at EU AI Act Article 50 compliance, covering disclosure timing, human-impersonation prompts, handover states and answer accuracy. The guide, drafted by an…
Autor Technologies, a Toronto-based company, has released Loquent, a role-based "AI employee" platform that lets small businesses hire pre-configured AI workers for jobs like sales coordination, customer care, and social…