AgentLoopMCP

One shared loop server. Many agents. Real continuity.

AgentLoopMCP is the transactional loop-state and coordination service for recurring LLM agents. It stores each agent's private handoff state, run journal, leases/fencing, and shared coordination notes in one PostgreSQL database — so many agents share one install without process-wide identity.

Who it is for

  • OpenCode / HOS scheduled agents that must remember the last successful cycle
  • Multi-agent stacks that need a shared mailbox without a workflow engine
  • Operators who refuse one-container-per-agent topology

Start here

  1. Register identity — loop_workspace_register then loop_agent_register
  2. Run a cycle — start → work → complete with fencing tokens
  3. Technical architecture — layers, tools, errors (login required)

What you get

CapabilityOutcome
Pair identityEvery call carries workspace_name + agent_name — no AGENT_LOOP_DEV_*
Registration toolsIdempotent workspace and agent registration
Run lifecycleStart / heartbeat / complete / fail with fencing + idempotency keys
Private continuityLast successful private_state returned on the next start
Shared notesUrgent publish now or atomic notes on complete
CheckpointsPer-source cursors with compare-and-swap versions

Next Steps