Token World¶
A universe simulator where LLM-powered agents inhabit a text-based world with procedurally generated mechanics.
Overview¶
Token World is a simulation engine where LLM-powered agents interact with a text-based environment whose rules emerge on-the-fly. The engine interprets agent actions, maps them to existing mechanics or generates new ones as executable Python code, and returns observations grounded entirely in the knowledge graph.
From a resident agent's perspective, the world feels fully real -- every observation derives from actual graph state and mechanic execution. There is no hallucinated or ungrounded state.
Key Concepts¶
Knowledge Graph¶
All world state lives in a schema-less property graph powered by NetworkX. Nodes and edges carry arbitrary key-value attributes with no upfront schema. If it's not in the graph, it doesn't exist.
Mechanics¶
World rules are Python functions generated by LLMs and executed deterministically. Each mechanic:
- Checks preconditions against the current graph state
- Applies side effects that mutate the graph
- Produces mutations that are logged for replay and rollback
Resident Agents¶
LLM-powered inhabitants that perceive and act within the world through natural language. Each agent maintains its own memory and session history.
Simulation Engine¶
Orchestrates the core tick loop:
- Agent produces an action (natural language)
- Engine classifies and interprets the action
- Engine matches to an existing mechanic or pauses for generation
- Mechanic executes against the knowledge graph
- Engine generates a grounded observation from the updated state
Navigation¶
- Architecture -- System component diagrams and core simulation loop
- Getting Started -- Installation and first steps