agent-memory
Universal memory architecture for AI agents. Provides long-term memory, daily logs, diary, cron inbox, heartbeat state tracking, social platform post tracking, sub-agent context patterns, and adaptive learning -- everything an agent needs for identity continuity across sessions.
Why use this skill?
Give your AI agent persistent memory and identity across sessions. Learn how to implement long-term storage, daily logs, and state tracking for improved AI performance.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/psychotechv4/jarvis-memory-architectureWhat This Skill Does
The agent-memory skill provides a persistent, file-based cognitive architecture for OpenClaw agents. It transitions your AI from a stateless assistant into an entity with continuity, enabling the storage of long-term wisdom, daily activity logs, and cross-session state tracking. By organizing data into specific categories—such as curated memories in MEMORY.md, daily logs in the memory/ directory, and automated heartbeat states—the agent can effectively 'remember' its history, track its progress on projects, and manage recurring tasks through the cron inbox system.
Installation
To integrate this memory architecture, use the following command in your terminal within your OpenClaw environment:
clawhub install openclaw/skills/skills/psychotechv4/jarvis-memory-architecture
Use Cases
- Long-term Project Continuity: Maintain context over weeks or months, ensuring the agent doesn't lose track of codebase details or infrastructure settings.
- Reflective Learning: Use the diary and strategy notes to document what worked or failed, allowing the agent to refine its operations over time.
- Automated Task Management: Use the cron-inbox and heartbeat-state to synchronize automated background checks with your manual sessions, avoiding redundant operations.
- Identity Stability: Build a consistent personality and set of preferences that evolve based on user feedback and recorded interactions.
Example Prompts
- "Review my MEMORY.md and summarize the top three lessons I've learned about project optimization this month."
- "Log today's activities into the current daily memory file: we successfully deployed the API update and fixed the CORS issue."
- "Check the heartbeat state for the email service and tell me how long it has been since the last sync."
Tips & Limitations
- Maintenance is Key: Periodically summarize raw daily logs into your main memory file to prevent clutter and ensure the agent can retrieve important context efficiently.
- Data Sensitivity: Since the memory file is persistent, avoid storing sensitive credentials in plaintext within these files unless you have an external encryption layer.
- Context Windows: While this architecture provides excellent retrieval capabilities, be mindful of how much data you feed into the LLM prompt at once; load only relevant segments to optimize cost and performance.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-psychotechv4-jarvis-memory-architecture": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read