mental-model-ha
CommunityPreserve and restore multi-agent mental models.
Software Engineering#multi-agent#compaction#librarian#high-availability#session-logs#mental-model#restore-protocol
Authormvschwarz
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Preserves and restores a pod's shared mental model across compaction events and session restarts, ensuring continuity of multi-agent work across the lifecycle of a rig.
Core Features & Use Cases
- The filesystem serves as durable memory, externalizing scope knowledge, session logs, and restore artifacts to survive compaction and restart.
- The filesystem is multiplayer: scope folders are readable and writable by every agent, enabling cross-agent restoration.
- One place for everything: artifacts are centralized to support consistent restoration, governance, and reasoning across pods and roles.
- Phased Restore Protocol guides post-compaction recovery, validation, and dialogue-based synchronization between peers.
- Continuous state maintenance: regular updates to scope-knowledge, session logs, and restore artifacts to keep memory fresh.
Quick Start
Boot a demo rig and review the pod session logs to begin practicing continuous mental-model maintenance.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: mental-model-ha Download link: https://github.com/mvschwarz/openrig/archive/main.zip#mental-model-ha Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.