Agent Protocols news and analysis on Web Pulse: 3274 curated articles tracking the latest Agent Protocols developments, tools, and research, updated continuously from vetted sources.
Google said Thursday that Universal Cart, a tool that lets users collect and monitor products found across Search and in the Gemini app, is now available to U.S. users, following its preview at Google I/O in May. The car…
OGX, the open-source agentic API server formerly known as Meta's Llama Stack, has been rebranded with a model-agnostic, multi-SDK, production-grade mission, according to its GitHub page. The MIT-licensed project has over…
ServiceNow announced AI Passport, a new authority layer that gives enterprises runtime control over what AI agents and Model Context Protocol (MCP) servers are authorized to do at every point in a multi-agent workflow. S…
A developer published a guide on getting better planning results from Claude Opus and Sonnet, arguing that model choice matters less than giving the model live schedule data, short constraint-focused prompts, and persist…
Developer jckodel released FACE, a single Go binary that serves a local browser window on 127.0.0.1 over coding agents via the Agent Client Protocol (ACP) that Zed published, connecting to the official CLIs of Claude Cod…
Drupal creator Dries Buytaert exposed his 20-year-old custom photo album module's operations as AI-callable tools using the contributed Tool module's Tool API, which generates JSON Schema from PHP attributes on plain PHP…
Druid AI announced on October 14, 2026 a 26-component governance reference model for enterprise agentic AI, citing an Agentic AI Institute finding that 60% of current production deployments lack adequate governance. The …
Atlassian and OpenAI announced an expanded partnership on October 14, 2026, making OpenAI's GPT-6 Astra and GPT-5.6 frontier models the primary intelligence layer for agents across the Atlassian ecosystem and Rovo. Atlas…
A developer built Mill, a local-first AI operations assistant for meal-prep side hustlers that connects an OpenAI- or Ollama-backed agent to a local SQLite database through 16 typed FastMCP tools. The system tracks pantr…
Server-noonien has launched as a drop-in replacement for the official @modelcontextprotocol/server-memory knowledge graph that syncs agent memory across machines peer-to-peer via the nooniend daemon, with no central serv…
A curated directory of official Model Context Protocol (MCP) servers has launched, listing only servers built by the company behind each product or by widely used open source projects, with vendor MCP documentation linke…
NVIDIA has open-sourced Run:ai, its AI workload and GPU orchestration platform for Kubernetes, publishing the control plane, cluster services, installer, CLI, MCP server, documentation, shared client packages, and local …
A practical guide outlines how to run the Model Context Protocol (MCP) in production, describing a three-component architecture of MCP host, client, and server for connecting AI agents to external tools. It recommends st…
Graphify, an open source CLI, builds a local knowledge graph of a codebase so AI coding agents can navigate files, functions and dependencies instead of repeatedly grepping. It installs via uv, pipx or pip, supports Curs…
Databricks' Genie One and Genie Code AI coworkers draw enterprise context from four distinct places, according to a Databricks walkthrough: company-wide facts go in Genie Ontology, team rules in instructions files, repea…
Kerno released Kerno v1, an AI runtime QA engineer that tests backend user flows, APIs, MCP servers and queues against real databases and services from inside Claude Code, Cursor and Codex. Kerno reports that teams using…
Mitchell Hashimoto published OSC 7501, a terminal escape sequence letting programs report idle, working, blocked, done or error status, on 6 October 2026, and three coding agents shipped support within two days: Pi 1.1.0…
Make0 AI launched a plug-and-play memory layer that connects to any AI agent via MCP, letting agents read and write a shared graph-based "Brain" so context persists across tools like Codex and Claude Code. The developer …
A bespoke gateway built with the Microsoft 365 Agents SDK in front of Microsoft Foundry hosted agents lets Teams agents receive message reactions and send proactive messages, use cases the default Foundry-to-Azure-Bot-Se…
RubyLLM 2.1, released by the RubyLLM project, adds an MCP client, typed judgments via TypeSafe's Jev models, agent evaluations, OpenTelemetry tracing, and mid-conversation provider switching, while cutting per-call work …