Are you an LLM? Read llms.txt for a summary of the docs, or llms-full.txt for the full context.
Skip to content
Core

State Management Surface

Run-scoped state routes for variables and concepts, plus deprecated planning state (goals / actions / cycles).

MuBit is primarily a memory engine. It also exposes a small set of run-scoped state routes (variables, concepts) that are useful when you want to persist orchestrator state next to memory.

A broader planning surface (goals, actions, decision cycles) is still wired for backward compatibility but is deprecated — most workflows are better served by external task / orchestration systems.

ℹ️Note

For most use cases, start with remember, recall, getContext, checkpoint, and the learning-loop APIs. Reach for these state routes only when memory alone isn't enough.

Supported state surfaces

DomainPurposeStatus
VariablesSmall explicit run-scoped state values that memory shouldn't inferSupported
ConceptsNamed planner concepts / controlled vocabularySupported

Variables routes

RouteMethodPurpose
/v2/control/variables/setPOSTSet a run-scoped variable
/v2/control/variables/getPOSTGet a variable
/v2/control/variables/listPOSTList variables for a run
/v2/control/variables/deletePOSTDelete a variable

Concepts routes

RouteMethodPurpose
/v2/control/concepts/definePOSTDefine a concept
/v2/control/concepts/listPOSTList concepts

Deprecated planning surfaces

⚠️Warning

The goals, actions, and decision-cycle RPCs are deprecated. They remain wired for existing deployments but are no longer recommended.

  • Goals — Track tasks in a dedicated system (Linear, Jira, Asana). MuBit should store the lessons and outcomes, not the task list.
  • Actions / decision cycles — Delegate to your agent orchestration framework (LangGraph, CrewAI, ADK). Persist only the resulting lessons, outcomes, and traces in MuBit.

If you're currently using these routes, keep them running — they aren't being turned off — but plan to migrate the planning surface to external tools and keep MuBit focused on experiential memory.

CapabilityRoutesReplacement
Goals/v2/control/goals/add, /v2/control/goals/update, /v2/control/goals/list, /v2/control/goals/treeExternal task tracker (Linear, Jira). Store only the resulting lessons / rules / mental models in MuBit.
Actions/v2/control/actions/submit, /v2/control/actions/logAgent framework execution log (LangGraph, CrewAI). Use archive + dereference when you need exact trace fidelity.
Decision cycles/v2/control/cycles/run, /v2/control/cycles/historyAgent framework planning loop. Record the outcome of each cycle via record_outcome / record_step_outcome.

Recommended usage guidance

  • Keep variables and concepts in the same run_id as the memory they explain.
  • Move goals, actions, and decision cycles to your task / orchestration system of record.
  • Record the learning signal that comes out of those systems (outcomes, lessons, rules) in MuBit so future runs benefit.
  • Use checkpoint when a long run is about to compact or cross a risky boundary.

Failure modes and troubleshooting

SymptomRoot causeFix
Planner state exists but the model still forgets thingsOnly state was stored, not memoryPersist facts, lessons, or rules alongside variables
Debugging is hardActions / cycles are missingRecord planner decisions in your orchestration framework and surface outcomes to MuBit
Variable list grows unboundedNo TTL disciplineUse variables/delete at end-of-run or namespace by session

Next steps