vbot-mind

name	vbot-mind
description	Create and control autonomous virtual robots (V-Bots) with perception, LLM-driven reasoning, episodic memory, and personality engines. Use when working with Godot, Unity3D, or Resonite V-Bots.

V-Bot Mind — Skill

What This Server Does

V-Bot Mind is the fleet's autonomous virtual robot brain runtime. It receives perception data from a game engine (what the bot sees, hears, senses), runs LLM reasoning to decide what to do, maintains episodic memory of past interactions, and outputs motor commands back to the engine.

You use this server when you have V-Bots in Godot, Unity3D, or Resonite that need autonomous behavior — NPCs that think, remember, and act like characters.

Core Workflow

1. Create a V-Bot with a name, personality, role, and backstory
2. Perceive — feed the bot observations from the game engine
3. Think — run LLM reasoning on the current situation
4. Act — output motor commands back to the engine
5. Remember — store important events; query past memories
6. Chat — have a player/NPC talk directly to the V-Bot

Tool Reference

vbot_mind (primary portmanteau)

Operations:

• status — List all V-Bots or get one by id
• create — Create a new V-Bot with personality, role, and backstory
• configure — Update a V-Bot's personality, goals, or role
• perceive — Feed observations (what the bot sees/hears/senses)
• think — Run LLM reasoning on the current situation
• act — Execute a motor command (move, speak, interact, idle)
• chat — Direct conversation with a V-Bot
• remember — Store or retrieve episodic memories
• delete — Remove a V-Bot instance

vbot_agentic_workflow

Runs a multi-step perceive → think → act loop toward a goal. The V-Bot autonomously pursues the goal for up to max_steps cycles.

Personality Design

V-Bot personalities are defined by trait keywords and a backstory:

• Traits: curiosity, sociability, aggression, patience, humor, diligence, caution, creativity
• Backstory: A short narrative that shapes the bot's worldview and behavior

The LLM uses the personality + backstory + episodic memory to generate consistent, in-character responses. A "shy, cautious" bot will behave differently from a "bold, aggressive" one in the same situation.

Fleet Pipeline Integration

World Labs (generate world) → Godot (assemble scene) → V-Bot Mind (populate with NPCs)
                                                              │
MuJoCo (train locomotion) → V-Bot Mind (behavior) → Godot (render + physics)
                                                              │
                                             Teleoperator-MCP (HMD interaction)

Best Practices

• Create V-Bots with distinct personalities — contrast makes worlds feel alive
• Feed rich perception: "The player in red armor enters the forge" beats "Someone is here"
• Store important memories at "high" priority; trivial observations at "low"
• Use agentic workflow for multi-step quests; use individual think/act for real-time loops
• Poll the V-Bot registry (status) before creating duplicates