Three days ago, Microsoft open-sourced the Agent Governance Toolkit — seven packages, five language SDKs, sub-millisecond policy enforcement.
Most agent loops work like this: the model picks a tool, calls it, gets the result, picks the next tool. Rinse, repeat.
A 3.4 GB model just posted a 97.
Over the past three months, OpenAI retired Swarm and shipped the Agents SDK with first-class handoffs.
The MCP Dev Summit kicked off in New York today with 95 sessions about protocols, security, and scaling agent infrastructure.
For the past year, MCP gave agents a way to reach tools. Good.
A year ago, people were debating whether MCP would become the standard for connecting LLMs to tools. That debate is over — MCP won.
Most multi-agent failures trace back to orchestration bugs and handoff engineering, not model capability -- UC Berkeley's MAST framework found that 79% of...