
AI agents are shipping to prod, but most stacks lack agent security.
Meet Agent Governance Toolkit: policy enforcement, zero‑trust identity, sandboxing, SRE for agents. Covers all 10 OWASP risks. MIT licensed. msft.it/6012QNzLq
English
Open at Microsoft
6.8K posts

@OpenAtMicrosoft
All things #OpenSource at Microsoft https://t.co/4V3rben8iJ






Today we launch the Agentic AI Foundation (AAIF) with project contributions of MCP (@AnthropicAI), goose (@blocks) and AGENTS.md (@OpenAI), creating a shared ecosystem for tools, standards, and community-driven innovation. Learn more about this major step toward: hubs.la/Q03Xvw3v0


















