Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From agentmind
Implements self-learning memory system for OpenClaw AI agents that detects preferences, workflows, and code styles from interactions. Useful for reviewing learned behaviors or leveraging prior knowledge in sessions.
npx claudepluginhub youhai020616/agentmind --plugin agentmindHow this skill is triggered — by the user, by Claude, or both
Slash command
/agentmind:agentmind-openclawThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Self-learning memory system that makes AI agents understand you better over time.
Observes Claude Code sessions via hooks to create atomic instincts with confidence scoring, then evolves them into reusable skills, commands, or agents.
Observes Claude Code sessions via hooks to create atomic instincts with confidence scoring, then evolves them into reusable skills, commands, or agents.
Creates p5.js generative art with seeded randomness, noise fields, and interactive parameter exploration. Use for algorithmic art, flow fields, or particle systems.
Share bugs, ideas, or general feedback.
Self-learning memory system that makes AI agents understand you better over time. Automatically detects your preferences, workflows, and code style from interactions.
Use when user asks about learned preferences, wants to review agent behavior patterns, or when starting a session that should leverage previously learned knowledge.
/agentmind status — Show learning overview/agentmind instincts — List learned behaviors/agentmind evolve — Trigger evolution cycle/agentmind preferences — Show detected preferences/agentmind approve <id> — Approve a learned behavior/agentmind reject <id> — Reject a learned behaviorUnlike the Claude Code plugin which uses lifecycle hooks, the OpenClaw adaptation works through:
memory/*.md files and conversation history to detect patternsanalyze to discover new patterns from recent interactions# Install as OpenClaw skill
cp -r skills/agentmind-openclaw ~/.openclaw/skills/agentmind/
# Create cron for periodic learning (every 6 hours)
openclaw cron create --name "AgentMind Learn" \
--schedule "0 */6 * * *" \
--task "Run AgentMind analysis on recent memory files"
~/.openclaw/workspace/agentmind/instincts.json~/.openclaw/workspace/agentmind/observations/AgentMind complements OpenClaw's built-in memory_search (pull-based) with
push-based injection — high-confidence instincts are automatically included
in the agent's context without needing to search for them.