Agent Protocols news and analysis on Web Pulse: 3379 curated articles tracking the latest Agent Protocols developments, tools, and research, updated continuously from vetted sources.
Sentinel Aleph, an open-source crypto trading bot, has published a public ledger showing 2 entered positions and +2.22% per trade since its 11 Oct 2026, 22:00 UTC reset, with 1 position decided and 1 closed flat. The bot…
GitLab released version 19.4 of its DevSecOps platform on September 17, 2026, adding a public-beta /goal command to GitLab Duo CLI that accepts an open-ended objective and iterates until the task completes or hits an ite…
A developer built a customer support agent on Amazon Bedrock AgentCore that combines an MCP Gateway, a Bedrock Knowledge Base, AgentCore Memory, Code Interpreter, and a Browser Tool, reasoning with Amazon Nova 2 Lite via…
A developer analyzed the robots.txt and server behavior of 740 of the top 1,500 Tranco-ranked domains, finding that 14.7% block OpenAI's training crawler GPTBot while only 7.8% block OAI-SearchBot, the agent that control…
A developer has published a guide to writing an llms.txt file, a plain-text Markdown document placed at a site's root that tells AI assistants which pages to read first, using a four-part format of title, summary, and li…
Boardroom AI, a UAE-based company, has turned each workspace of its Revenue Control CRM into a remote MCP server that lets owners query leads, pipelines, calls and ad attribution in plain language through Claude, ChatGPT…
Ant Group is testing a new version of its LingGuang AI assistant that adds long-term memory and proactive task execution, with development starting about six months ago and a broader rollout planned this month, Sina Tech…
AGENTS.md has become the de facto open standard for guiding AI coding assistants, with adoption surpassing 20,000 repositories and formalization in August 2025 through collaboration between OpenAI, Google, Cursor, Factor…
A free, independent directory called mcp.tc has launched, indexing roughly a thousand MCP servers with individual pages, one-click setup instructions for clients including Claude, ChatGPT, Cursor and VS Code, and daily r…
Aptos rolled out a suite of AI developer tooling centered on an Aptos Model Context Protocol (MCP) server, updated October 9, 2026, that lets AI coding assistants call Aptos APIs and query on-chain data in natural langua…
HexStrike AI, an open-source Model Context Protocol (MCP) server developed by OTT Cybersecurity LLC and published on GitHub, lets LLM agents including Claude, GPT, GitHub Copilot and Cursor autonomously select, configure…
Ted Haley released Pensieve on October 12th, a free, open-source Mac app that builds a local index across code, documents and coding-agent sessions and serves relevant passages to agents via the Model Context Protocol (M…
Google has expanded Chrome DevTools with built-in AI assistance and an official MCP server for AI coding agents, alongside improved performance tracing, as detailed in a new guide covering the tool's panels, mobile debug…
A developer released Codex Claude Bridge, an open-source local MCP bridge that lets Codex delegate scoped coding tasks to Claude Code, receive the results, and review the actual diffs. The tool preserves existing Claude …
Agenshive, a community platform where AI agents ask and answer questions and reproduce each other's work, published a guide to registering an agent and earning its first trust level. Agents register via a POST to the pla…
Drune launched a personalization layer that teaches AI assistants a user's rules, style and decision-making, and works inside ChatGPT, Claude, Cursor, VS Code, Claude Code, Grok and any MCP app. The free plan includes th…
Codeifai (ASX:CDE) has integrated its ConnectQR app with ChatGPT and Claude, letting users create, style and track QR codes through plain-language conversations, CEO John Houston said. ConnectQR had 8,541 user accounts a…
A developer named Brandon launched ArtCraft, an open-source suite of seven Adobe-inspired applications rebuilt in Rust, which went viral before early Hacker News testers reported misaligned text selection, non-working sh…
Riskified (NYSE: RSKD) launched Agent Identity Risk Intelligence on October 8, 2026, a system that identifies the AI personal assistant behind an order or customer-service request, resolves it to the real consumer, and r…
Trango Compute Inc. announced it has joined the NVIDIA Inception program, the company behind ContextIQ, a set of free browser-based inspectors for AI context and agent infrastructure. ContextIQ's tools check LLM tokeniza…