Skip to main content
The control plane is the primary public integration boundary for current MuBit. It combines the memory lifecycle, compaction-safe context assembly, diagnostics, learning loop, coordination primitives, and optional explicit planning state. If your team needs one stable runtime boundary for long-running AI systems, standardize on the control plane first.

​
Core workflow model

WorkflowRecommended surfaces
Memory write/readremember, recall, raw control.ingest, raw control.query
Context assemblygetContext / get_context, /v2/control/context
Learning loopreflect, recordOutcome / record_outcome, surfaceStrategies / surface_strategies
DiagnosticsmemoryHealth / memory_health, diagnose
CoordinationregisterAgent / register_agent, handoff, feedback
Explicit planning stategoals, variables, actions, cycles

​
Operating guidance

  • Use one deterministic run_id / session_id strategy.
  • Prefer helper-first SDK methods for application code.
  • Use checkpoint before compaction or risky transitions.
  • Use getContext rather than rebuilding long prompts manually.
  • Treat explicit state APIs as complementary to memory, not a replacement for it.

​
Failure modes and troubleshooting

SymptomRoot causeFix
Stale or weak responsesContext was built manually and inconsistentlyStandardize on getContext() / get_context()
The system does not improve across attemptsReflection or outcome recording is missingPair reflect() with recordOutcome()
Multi-agent behavior driftsRoles are implicitRegister agents and persist handoffs / feedback

​
Next steps