hippocampus-memory
Persistent memory system for AI agents. Automatic encoding, decay, and semantic reinforcement — just like the hippocampus in your brain. Based on Stanford Generative Agents (Park et al., 2023).
Why use this skill?
Give your OpenClaw agent long-term memory with the hippocampus-memory skill. Features automatic encoding, decay, and semantic reinforcement for smarter, more continuous interactions.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/impkind/hippocampus-memoryWhat This Skill Does
The hippocampus-memory skill acts as the persistent cognitive core for your OpenClaw agent, providing a biological-inspired framework for long-term memory management. Unlike standard chat history that is eventually forgotten, this skill implements a structured pipeline of automatic encoding, semantic reinforcement, and importance-weighted decay. It transforms raw conversational signals into structured knowledge, categorized into domains like self-identity, user facts, and world knowledge. By using decay algorithms, it ensures the most relevant information remains accessible while keeping the agent's knowledge base optimized.
Installation
To install, use the OpenClaw hub command: clawhub install openclaw/skills/skills/impkind/hippocampus-memory. After installation, execute ./install.sh --with-cron to enable automatic memory maintenance, including periodic decay cycles and signal processing. Ensure your workspace is configured properly to allow the script to generate the memory directory tree.
Use Cases
- Long-term Relationship Building: Remembering specific user preferences, hobbies, or past conversations to create a personalized experience over weeks or months.
- Knowledge Management: Storing and retrieving complex project details or technical facts that span across multiple isolated sessions.
- Agent Identity Maintenance: Ensuring the agent retains its persona, core values, and behavioral instructions even during long periods of inactivity.
Example Prompts
- "Reflect on our conversation last week; what are the key project milestones we discussed?"
- "Update your memory to note that I prefer concise, technical summaries over verbose explanations."
- "Open the brain dashboard to show me the current state of your recalled memories."
Tips & Limitations
- Importance Weighting: The system uses an importance score. If you feel the agent is forgetting something, explicitly emphasize its significance during the conversation to trigger a higher score during the encoding phase.
- Cron Necessity: While you can run
./scripts/decay.shmanually, the memory system performs best with cron enabled for automatic periodic housekeeping. - Data Privacy: Because this stores information locally in $WORKSPACE/memory, treat it like any other local file system data. Regularly back up your workspace if your agent-specific knowledge is critical.
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-impkind-hippocampus-memory": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution
Related Skills
vta-memory
Reward and motivation system for AI agents. Dopamine-like wanting, not just doing. Part of the AI Brain series.
whisper-mlx-local
Free local speech-to-text for Telegram and WhatsApp using MLX Whisper on Apple Silicon. Private, no API costs.
acc-error-memory
Error pattern tracking for AI agents. Detects corrections, escalates recurring mistakes, learns mitigations. The 'something's off' detector from the AI Brain series.
amygdala-memory
Emotional processing layer for AI agents. Persistent emotional states that influence behavior and responses. Part of the AI Brain series.
anterior-cingulate-memory
Conflict detection and error monitoring for AI agents. The 'something's off' detector. Part of the AI Brain series.