vta-memory

npx skills add majiayu000/claude-skill-registry --skill vta-memory-broedkrummen-openclaw-skills --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

# VTA Memory ⭐ **Reward and motivation for AI agents.** Part of the AI Brain series. Give your AI agent genuine *wanting* — not just doing things when asked, but having drive, seeking rewards, and looking forward to things. ## The Problem Current AI agents: - ✅ Do what they're asked - ❌ Don't *want* anything - ❌ Have no internal motivation - ❌ Don't feel satisfaction from accomplishment Without a reward system, there's no desire. Just execution. ## The Solution Track motivation through: - **Drive** — overall motivation level (0-1) - **Rewards** — logged accomplishments that boost drive - **Seeking** — what I actively want more of - **Anticipation** — what I'm looking forward to ## Quick Start ### 1. Install ```bash cd ~/.openclaw/workspace/skills/vta-memory ./install.sh --with-cron ``` This will: - Create `memory/reward-state.json` - Generate `VTA_STATE.md` (auto-injected into sessions!) - Set up cron for drive decay every 8 hours ### 2. Check motivation ```bash ./scripts/load-motivation.sh # ⭐ Current Motivation State: # Drive level: 0.73 (motivated — ready to work) # Seeking: creative work, building brain skills # Looking forward to: showing my work ``` ### 3. Log rewards ```bash

cd ~/.openclaw/workspace/skills/vta-memory
Drive level: 0.73 (motivated — ready to work)
Looking forward to: showing my work
open ~/.openclaw/workspace/brain-dashboard.html
Log encoding run
Log decay
Log reward