Microsoft RAMPART: pytest-native safety and security testing framework for agentic AI
Microsoft has released RAMPART, an open-source Python framework for safety and security testing of agentic AI applications, built natively on pytest. The repository is gaining traction on GitHub with 301 total stars and 77 new stars today. It targets the growing need for structured evaluation tooling specifically designed for AI agents rather than traditional software.
Related guides (4)
Related events (8)
PentestAgent: AI Agent Framework for Black-Box Security Testing
PentestAgent is an open-source Python framework that applies AI agent techniques to penetration testing, bug bounty, and red-team workflows. The project has accumulated 2,497 GitHub stars with modest daily traction (+30). It represents a practical deployment of autonomous agent architectures in offensive security contexts.
Microsoft RD-Agent: automated AI-driven R&D for data and model development
Microsoft has released RD-Agent, an open-source Python framework aimed at automating high-value R&D processes in AI, with a focus on data and model development. The project positions AI as the driver of data-driven AI workflows, targeting industrial productivity use cases. With 13,500 GitHub stars, it has attracted meaningful community interest, and a technical report is available.
Microsoft Agent Governance Toolkit: Policy Enforcement and Zero-Trust Security for Autonomous AI Agents
Microsoft has published an open-source Agent Governance Toolkit on GitHub covering policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. The toolkit claims full coverage of the OWASP Agentic Top 10 security risks. It has accumulated 1,828 stars with 113 added today, indicating active community interest. This positions Microsoft as a contributor to emerging standards for safe agentic AI deployment.
Microsoft agent-framework: open-source library for building and orchestrating AI agents
Microsoft has published an open-source framework on GitHub for building, orchestrating, and deploying AI agents and multi-agent workflows, with support for both Python and .NET. The repository has accumulated 11,061 stars. It represents Microsoft's entry into the agent harness tooling space alongside existing frameworks like LangChain and AutoGen.
NVIDIA releases SkillSpector: security scanner for AI agent skills
NVIDIA has published SkillSpector, an open-source Python tool for scanning AI agent skills to detect vulnerabilities, malicious patterns, and security risks. The repository is trending on GitHub with 1,920 total stars and 280 added today. The tool addresses an emerging security concern as agentic AI systems proliferate and third-party skill/tool ecosystems grow.
pydantic/pydantic-ai: AI Agent Framework Trending on GitHub
pydantic-ai is an open-source AI agent framework built by the Pydantic team, applying Pydantic's data validation patterns to AI agent construction. The repository has accumulated 17,238 stars with modest daily momentum (+16 today). It represents a community-level signal of interest in structured, type-safe agent tooling in Python.
Meta Publishes Advanced AI Scaling Framework and Safety & Preparedness Report for Muse Spark
Meta has released an updated Advanced AI Scaling Framework that expands risk evaluation categories—including chemical/biological threats, cybersecurity, and loss-of-control risks—and introduces formal Safety & Preparedness Reports tied to specific model deployments. The first such report covers Muse Spark, Meta's advanced reasoning model, detailing pre- and post-safeguard evaluations across severe risk categories and ideological balance. Meta also describes a shift in safety methodology: rather than scenario-specific refusal training, Muse Spark is trained on the reasoning behind safety principles, enabling more generalizable behavior in novel situations. The framework applies across open, API, and closed deployments.
Anthropic-Cybersecurity-Skills: 754 Structured Cybersecurity Skills for AI Agents
A GitHub repository providing 754 structured cybersecurity skills designed for AI coding agents, mapped to five major frameworks including MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, and NIST AI RMF. The skills are organized across 26 security domains and conform to the agentskills.io standard. The project claims compatibility with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI, and 20+ other platforms. It has accumulated 7,330 stars with 238 added today, indicating notable community traction.