MCP Pro Hosted: Connect in One Step, Nothing to Install
MCP exposure without admission control is an open door, and the old answer made the user build the door. That is the […]
Agency Check: Test the Agent Before It Acts
An agent should not act until it has passed a check. That is the verdict. Agency Check is the check, and it […]
AI SAFE2 CLI 1.0: Evidence You Can Inspect, Decisions Humans Still Own
CLI 1.0 is the release where agent governance stopped being a document and became evidence you can inspect. Version 1.0.1 is the […]
AI SAFE2 v3.1 Agent CLI, AISM Decision Support, and UAS
September 4, 2026 is the day the framework stopped being a document and became a tool agents could run. AI SAFE2 v3.1 […]
Lovable Sovereign Runtime: Vibe Coding Needs a Boundary Before the First Prompt
The prior design had five surfaces. It missed the sixth, and the sixth was the one that mattered. Lovable subagents read all […]
Cursor Sovereign Runtime: The Editor That Writes Code Needs a Gate on Every Line
Cursor has the most complex CVE record of any platform in this series: 11-plus disclosed vulnerabilities, one currently unpatched, and four distinct […]
CrewAI Sovereign Runtime: The Crew Answers to the Boundary, Not Each Other
A crew is several agents working one job, passing outputs between them. That is what makes CrewAI useful, and it is what […]
Make.com Sovereign Runtime: An Injection in One Module Rides the Whole Chain
Make is not a Python runtime or a CLI. It is a visual canvas where modules chain automatically: webhook output becomes AI […]
AutoGen Sovereign Runtime: Multi-Agent Debate Needs a Referee
AutoGen is the one framework in this series where prompt injection does not stop at a bad answer. It becomes arbitrary code […]
Langflow Sovereign Runtime: The Visual Builder Gets a Boundary
Every other sovereign runtime in this series defends a platform that has a Python execution boundary you can wrap, a hook you […]
LangGraph Sovereign Runtime: The Graph Loops, So the Boundary Must Loop With It
A LangGraph agent does not run once and stop. It loops through steps, and state carries from one step to the next. […]
LangChain Sovereign Runtime: The Chain Stops Reading Its Own Instructions
A LangChain agent that takes its instructions from the documents it retrieves is not governed. It is exposed. The LangChain Sovereign Runtime, […]