Strands Box Open-source sandbox for AI agents that combines OS-level isolation with Dogwood policies able to condition permissions on what the agent has already done, such as blocking outbound HTTP after reading customer data. Credentials stay outside the agent process. Currently in developer preview on macOS.
Visit productFeatured media
Loading media…
View on XCosigns Received
“Promising architectural primitive for agent governance that unlocks safe autonomous workflows involving sensitive data and privileged enterprise systems.”