AI Agents news and analysis on Web Pulse: 49324 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Anthropic built a custom source control system called Scion after its daily merged code changes rose from about 2,500 in May 2026 to over 30,000 by September 2026, straining Git and its roughly 25 million daily CI checko…
Apple released Xcode 27.3 beta 1, adding GitHub Copilot to the IDE's built-in coding assistant, according to the release notes' Coding Intelligence section. The integration follows Apple's earlier additions of ChatGPT an…
A from-scratch browser and mobile rewrite of Heroes of Might and Magic III (1999) is fully playable end to end, covering the complete Shadow of Death and Horn of the Abyss content, with an early AI that the developer say…
RudderStack founder Soumyadeb said the company has open-sourced DevBox, an engineering harness it has used internally since April, and that roughly 35% of its merged PRs — more than 1,900 — have come from DevBox. DevBox …
Anthropic added Databricks MLflow as a supported destination for native OpenTelemetry export from the Claude Platform, letting developers using the Anthropic SDKs, the Messages API and Managed Agents send traces to Datab…
ClickUp has begun a gradual rollout of browser use in Brain, the AI built into its work platform, letting Brain open websites in its own browser and bring findings back into ClickUp; ClickUp has not given a date for full…
A YouBeyond project contributor flagged that the inline example's global tool-call ID check, which uses a set-based comparison of (trace_id, tool_call_id) pairs, would accept a single result even when two call declaratio…
AmpUp launched Enterprise Brain, a private-preview context layer for enterprise agents that stores company facts in a vertical-specific schema and rewrites task notes after every graded run, claiming 35.2% root-cause acc…
GitHub added Dependabot version update support for Agent Package Manager (APM), letting repositories automatically keep AI agent skills, prompts and instructions current. Dependabot now opens pull requests to update supp…
Anthropic's Project Glasswing, launched April 7th, 2026 with access to the unreleased frontier model Claude Mythos Preview, had by May 22nd produced more than 10,000 high- or critical-severity software flaws across about…
Apple announced that developers can now integrate Siri AI's new features into "all apps" through the iOS 27.3 Developer Preview, letting the voice assistant use personal context, natural language prompts, and on-screen a…
Intology's automated research system Locus developed scientific AI models that outperformed state-of-the-art expert solutions across molecular scoring and design tasks, the company said in a thread on X. Intology tested …
Elon Musk said on November 1, 2026 that running Grok Bot, the personal AI assistant SpaceX launched in August 2026 under its xAI initiative, is "unsustainably high relative to revenue," and suggested the company is cutti…
Apple warned in its annual filing that AI agents could exceed their permissions, resist instructions, or take actions that are difficult to reverse, describing the risk as agents behaving in "unintended or unpredictable"…
A security guide details how apps built with AI coding tools like Lovable, Bolt, Replit and Cursor can leak secret API keys—Stripe live keys, OpenAI keys, Supabase service_role tokens and database credentials—into fronte…
The Headron project released an open-source infrastructure layer for AI agents built around three components: System 1 for context classification and capability routing, System 1.5 for deterministic policies, permissions…
A developer released Bruster, an open-source browser automation tool written in Rust that drives the platform's native webview instead of bundling a full Chrome instance, targeting AI agents and scripts. The controller r…
Anthropic released Message Threads in public beta on its Messages API as of November 2, 2026, letting Claude agents send only the new message per turn while the API caches the prior conversation server-side, which Anthro…
ZenML has introduced Kitaru, an agent harness that wraps existing agent frameworks in MLOps-style durable infrastructure, giving agents versioned artifacts, replayable execution graphs and observability hooks without req…
Traccia, a vendor-neutral Python SDK for runtime control of AI agents, is now available on PyPI, offering observability, evaluation and policy enforcement built on OpenTelemetry. The SDK's @govern decorator can deny or r…