AI Agents news and analysis on Web Pulse: 34921 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Google announced on September 21, 2026 that it has rebuilt its CC AI agent as a dedicated household coordination tool for families, running on isolated cloud infrastructure powered by Gemini AI and the Antigravity agenti…
A developer has added a component to their project that lets users dynamically declare HTTP endpoints which accept code, natural language, or a combination, execute the resulting code on the server, and return the respon…
Developer Sylwia Lask presented WebMCP, an experimental browser API that lets websites explicitly expose tools for AI agents to call, at AGNTCon + MCPCon Europe before an audience of over 2,000 attendees. She demoed AI C…
Maxim AI's Bifrost, an open-source AI gateway written in Go, is being positioned as a centralized MCP gateway for Anthropic's Claude Code CLI, aggregating multiple Model Context Protocol tool servers behind a single auth…
Jared Palmer released Kev, a family of small decision models built on Qwen3.5 in 0.8B, 4B, and 9B sizes, with pretrained weights, training code, and evaluation data available on GitHub. Kev's API matches TypeSafe's Syste…
A developer built an omnichannel shopping assistant that shares long-term memory between a text chat agent and a real-time voice agent using Amazon Bedrock AgentCore Memory, Strands, and Amplify Gen 2. The system uses Ag…
Google open-sourced AX (Agent Executor) this week, a distributed runtime that lets crashed AI agents resume from where they left off, released under the Apache 2.0 license on GitHub. The project reached 410 points on Hac…
A medical writer built the MDR Evidence Gap Agent, a demo that queries a synthetic Class III device dossier stored in Sanity to surface claims lacking linked clinical evidence and the EU MDR requirements they affect. The…
A benchmark of 50 product-classification tasks found that replacing an agentic LLM pipeline with TypeSafe's System One model, Jev, cut mean latency 86% from 9.62 seconds to 1.38 seconds and reduced model calls 56% from 7…
StepFun released Step 5 Preview, a sparse Mixture-of-Experts model with about 600B total parameters and about 27B activated per token, offering a 1M-token context window and text, image, and video input through a hosted …
A developer released TashevOS v0.1.0-alpha.1, the first public alpha of an Apache-licensed developer tool that provides project and Git discovery, AI detection for coding agents including Claude Code, Codex, Cursor, Gemi…
A Google Docs document titled "Thoughts on a Typesafe Coding Agent" was submitted to Hacker News, where it received 1 point and 0 comments. The document, linked via a Google Docs preview URL, discusses the concept of a t…
A developer has open-sourced AegisCrawler, a browser data-collection architecture that records semantic events via a Chrome extension and deterministically generates immutable, versioned, human-approved rules instead of …
A developer compared how Sanity, Notion, and Supabase handle AI agent write access, finding three distinct approaches: Sanity defaults to creating drafts before mutating published documents, Notion logs Custom Agent acti…
The Agent Memory Leaderboard opened Cycle 2 of the Agent Memory Challenge 2026 on September 20, offering over USD 22,000 in prizes to eligible open-source teams. The challenge evaluates long-term agent memory across thre…
OpenAI claimed on September 8 that it had solved the roughly 90-year-old Navier-Stokes problem, deploying 10,000 AI agents that completed the task in 88 hours, according to the company. Two teams — one composed of AI age…
A Hugging Face forum post by user Eric026 argues that multi-agent collaboration platforms are becoming an interesting direction for AI workflows, with teams assigning different tasks to multiple AI agents while humans co…
Vercel announced an integration on September 10, 2026, for building and deploying OpenAI Agents API applications, with OpenAI managing the agent loop and session state while Vercel connects each session to Vercel Sandbox…
AltSlate-Labs released find-jevable-code, an open-source agent skill for Claude Code and Codex that audits a repository for semantic decisions — routing, triage, relevance, and escalation — that could be replaced by Jev'…
MiniMax has open-sourced MiniMax Code, a terminal coding agent that understands projects, modifies files and runs tests from a command-line interface, with first-party code released under the MIT license. The repository …