Collected sources and patterns will appear here. Add from search or the patterns library.
AgentAction -> ExecutionResult
Run untrusted agent code and tools in a remote, isolated Docker-based sandbox host separate from the primary orchestrator.
Problem it solves
Executing untrusted agent-generated code or system commands directly risks compromising host security and consuming core platform resources.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.