_index.md

description	The root index for all MONITOR agent documentation.
tags	index root map
layer	0

MONITOR Documentation Map

Welcome to the MONITOR Agent Documentation. This structure is designed to be highly modular and dense to maximize context efficiency.

1. Product (What are we building?)

• Vision & Modes: The core pitch, modes of operation, and non-goals.
• Epics: The 9 core development epics and their coverage.
• Ideal State & Use Cases: Examples of how the three modes should ideally operate.

2. Architecture (How is it built?)

• The Three Layers: The strict 3-Layer Cake dependency rules.
• Layer 1: Data: Databases and tools.
• Layer 2: Agents: Specialized workers and DSPy.
• Layer 3: Interface: CLI and UI.
• MCP Transport: How agents communicate with data.

3. Loops & Systems (Dynamic Behaviors)

• Scene Loop: Turn-by-turn resolution.
• Story Loop: Campaign progression.
• Conversation Loop: NPC dialogue logic.
• World Building Loop: Collaborative creation.

4. Ontology (Data Models)

• Fact Canon Levels: How truth is managed.
• Entity Types: Archetypes vs Instances.
• Graph Relationships: How Neo4j nodes connect.

5. Infrastructure (DevOps & Env)

• Database Cluster: The docker-compose setup.
• Observability: Structlog and tracing.
• Lain MCP Proxy: How Lain integrates.

6. Reference & Guides

• Gameplay Examples & GM Craft: Narrative examples and design principles.
• Use Case Catalog: The full list of target workflows and specifications.

See Also

• AGENTS.md - The primary system instructions for agents.