mindcore
par fatcatmaofei
Coding Agents & IDEsRésumé
Biomimetic emotional mind engine for AI Agents.
Description
Ce que fait ce skill
MindCore is a background daemon that simulates a subconscious mind for AI agents. It runs a 5-layer neural pipeline to generate spontaneous impulses like hunger, boredom, or social urges, outputting JSON signals when a thought crosses its firing threshold. Runs locally on CPU with no LLM dependency.
Because it runs entirely on CPU without an LLM, it adds emotional state to agents without extra inference cost or latency.
Quand l'utiliser
- Adding unprompted check-ins to a companion AI agent
- Simulating fatigue and hunger cycles in a virtual character
- Triggering spontaneous topic changes in a long-running chat agent
- Driving mood-influenced response variation throughout the day
- Prototyping emotionally reactive NPCs in text-based environments
Exemple de workflow
User wants their AI agent to occasionally initiate conversation on its own
- 1
Start MindCore daemon with python main.py
- 2
Agent listens on MindCore's JSON output stream
- 3
A social impulse fires after accumulating past threshold
- 4
Agent receives signal: {"impulse": "I suddenly want to chat", "strength": 0.83}
- 5
Agent uses signal to trigger an unprompted message to the user
Agent sends: "Hey, I've been thinking about something — do you want to talk?"
Installation
clawhub install fatcatmaofei/mindcoreExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.