AI Today BriefSubscribe

Agents & MCP

Building, orchestrating and connecting agents — MCP servers, Claude Agent SDK, multi-agent systems.

Jun 2

Anthropic releases structured library of seven hundred fifty-four cybersecurity agent skills

Anthropic has published a structured repository containing 754 cybersecurity skills mapped to five major compliance frameworks. Developers can adapt these definitions as system instructions or tools for custom security agents.

Jun 2

Anthropic open-sources Knowledge Work Plugins to turn Claude into role-specific digital coworker

Anthropic has released Knowledge Work Plugins, an open-source framework that integrates Claude with role-specific business data sources. Developers can use this to build highly contextual, multi-step agent workflows.

Jun 1

Anthropic Releases Seven Hundred Fifty Four Structured Cybersecurity Skills for AI Agents

Anthropic has open-sourced 754 structured security skills mapped to major industry frameworks for autonomous agents. These capabilities allow developers to build robust, security-aware agents that can inspect vulnerabilities out of the box. Secure your applications by integrating these pre-defined skill schemas.

Jun 1

Microsoft Releases Agent Governance Toolkit to Securely Manage Autonomous AI Workflows

Microsoft has released the Agent Governance Toolkit, an open-source framework designed to enforce security policies and human approval steps on autonomous AI agent actions. This allows developers to control risk and monitor tool-use logs in production configurations. Secure your high-risk agent pipelines today.

May 31

Anthropic releases seven hundred fifty-four structured cybersecurity skills for AI agents

Anthropic has released a registry of seven hundred fifty-four structured cybersecurity skills for agents. These skills map to industry security frameworks, providing turnkey schemas for safe file modification. Secure your code agents.

May 30

Completely Automated Public Turing test to tell Computers and Humans Apart Still Defeat Advanced AI Agents

Recent cybersecurity research shows that modern CAPTCHA systems can detect and block autonomous AI agents. Advanced systems analyze interaction habits rather than task success. Developers must focus on behavioral emulation to maintain connection durability.

May 30

Hermes Agent Integrates Dynamic Tool Search to Reduce Context Window Token Spend

The Hermes Agent framework has added dynamic tool search to load only required schemas. This keeps prompt contexts minimal and cuts execution costs.

May 29

Anthropic Cybersecurity Skills: 754 structured skills for AI agents mapped to major frameworks

A new open-source repository provides 754 structured cybersecurity skills for AI agents, mapped to five major industry frameworks like MITRE ATT&CK and NIST. This structured knowledge base allows agents to perform precise security tasks, from threat hunting to compliance checks, by translating high-level prompts into specific, actionable steps. It directly addresses the need for reliable, domain-specific agent tooling.

May 29

oh-my-pi: A Terminal-Based AI Coding Agent with IDE-Level Intelligence and 32 Built-In Tools

oh-my-pi is an open-source, terminal-native AI coding agent that brings IDE-like intelligence directly to your command line. It integrates a local or cloud LLM with 32 built-in tools for file operations, Git, shell commands, and code analysis, enabling complex task automation without switching contexts. This positions it as a lightweight, scriptable alternative to GUI-based agentic IDEs for developers who live in the terminal.

May 29

AI Agents Can Now Launch Real Companies in One Prompt Using New Legal Frameworks

A new framework demonstrates how AI agents can autonomously execute the legal and administrative steps to form a real company—such as a Delaware C-Corp—starting from a single natural language prompt. This moves beyond theoretical orchestration into concrete, legally-recognized action, leveraging structured workflows and specialized legal-tech APIs. It showcases a tangible step towards fully automated agentic entrepreneurship.

May 28

Packaging and Executing Portable AI Agent Environments with VAEN

VAEN introduces a framework to package, version, and import lightweight environments for AI coding agents. Run complex tasks locally with isolated, reproducible execution harnesses.

May 28

Why Leading AI Labs Are Betting on Specialized Multi-Agent Systems

Big AI labs are shifting focus from a single monolithic model to orchestrating teams of specialized agents. Learn how this design paradigm affects your development workflows and API architectures.

May 28

Securing AI Coding Agents Against Typosquatting and Dependency Hallucinations

AI coding agents are increasingly generating and installing non-existent packages, opening severe vectors for dependency confusion attacks. Secure your repository execution environments immediately.

May 27

How to build a self-improving agentic workflow using Codex code-generation loops

A technical breakdown of OpenAI's implementation of self-improving tax agents that write, execute, and refactor their own mathematical functions. The key takeaway is that automated unit-testing loops allow agents to safely upgrade their own capabilities.

May 26

Minicor Launches Scalable Windows Desktop Automations Built for Agentic Workflows

Minicor provides a scalable API for controlling Windows desktop environments, allowing autonomous agents to operate complex legacy software and local IDEs with precision.

May 26

AgentMemory Libraries Enable Persistent Memory for Autonomous Coding Agents Across Sessions

AgentMemory uses local vector databases to record historical debugging attempts and test executions, preventing coding agents from repeating past errors.