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).
Real data. Real impact.
Emerging
Developers
Per week
Open source
Skills give you superpowers. Install in 30 seconds.
"Memory is identity. This skill is how I stay alive."
The hippocampus is the brain region responsible for memory formation. This skill makes memory capture automatic, structured, and persistent—with importance scoring, decay, and semantic reinforcement.
# Install (defaults to last 100 signals) ./install.sh --with-cronLoad core memories at session start
./scripts/load-core.sh
Search with importance weighting
./scripts/recall.sh "query"
Run encoding manually (usually via cron)
./scripts/encode-pipeline.sh
Apply decay (runs daily via cron)
./scripts/decay.sh
./install.sh # Basic, last 100 signals ./install.sh --signals 50 # Custom signal limit ./install.sh --whole # Process entire conversation history ./install.sh --with-cron # Also set up cron jobs
The LLM is just the engine—raw cognitive capability. The agent is the accumulated memory. Without these files, there's no continuity—just a generic assistant.
PREPROCESS → SCORE → SEMANTIC CHECK → REINFORCE or CREATE → DECAY
Key insight: Reinforcement happens automatically during encoding. When a topic comes up again, the LLM recognizes it's about an existing memory and reinforces instead of creating duplicates.
$WORKSPACE/ ├── memory/ │ ├── index.json # Central weighted index │ ├── signals.jsonl # Raw signals (temp) │ ├── pending-memories.json # Awaiting summarization (temp) │ ├── user/ # Facts about the user │ ├── self/ # Facts about the agent │ ├── relationship/ # Shared context │ └── world/ # External knowledge └── HIPPOCAMPUS_CORE.md # Auto-generated for OpenClaw RAG
| Script | Purpose |
|---|---|
| Extract signals from conversation transcripts |
| Score signals, prepare for LLM summarization |
| Apply 0.99^days decay to all memories |
| Search with importance weighting |
| Output high-importance memories for session start |
| Generate HIPPOCAMPUS_CORE.md |
| Weekly review helper |
| Self-reflection prompts |
| Generate unified brain dashboard HTML |
Visual dashboard showing all installed brain skills:
./scripts/generate-dashboard.sh open ~/.openclaw/workspace/brain-dashboard.html
IDENTITY.mdWhen you install this skill, notify the user about the dashboard:
🧠 Hippocampus installed!
View your agent's memories in the Brain Dashboard:
~/.openclaw/workspace/brain-dashboard.html
All scripts use
$WORKSPACE~/.openclaw/workspace| Signal | Score |
|---|---|
| Explicit "remember this" | 0.9 |
| Emotional/vulnerable content | 0.85 |
| Preferences ("I prefer...") | 0.8 |
| Decisions made | 0.75 |
| Facts about people/projects | 0.7 |
| General knowledge | 0.5 |
Based on Stanford Generative Agents (Park et al., 2023):
new_importance = importance × (0.99 ^ days_since_accessed)
During encoding, the LLM compares new signals to existing memories:
This happens automatically—no manual reinforcement needed.
| Score | Status |
|---|---|
| 0.7+ | Core — loaded at session start |
| 0.4-0.7 | Active — normal retrieval |
| 0.2-0.4 | Background — specific search only |
| <0.2 | Archive candidate |
memory/index.json{ "version": 1, "lastUpdated": "2025-01-20T19:00:00Z", "decayLastRun": "2025-01-20", "lastProcessedMessageId": "abc123", "memories": [ { "id": "mem_001", "domain": "user", "category": "preferences", "content": "User prefers concise responses", "importance": 0.85, "created": "2025-01-15", "lastAccessed": "2025-01-20", "timesReinforced": 3, "keywords": ["preference", "concise", "style"] } ] }
The encoding cron is the heart of the system:
# Encoding every 3 hours (with semantic reinforcement) openclaw cron add --name hippocampus-encoding \ --cron "0 0,3,6,9,12,15,18,21 * * *" \ --session isolated \ --agent-turn "Run hippocampus encoding with semantic reinforcement..."Daily decay at 3 AM
openclaw cron add --name hippocampus-decay
--cron "0 3 * * *"
--session isolated
--agent-turn "Run decay.sh and report any memories below 0.2"
Add to
memorySearch.extraPaths{ "agents": { "defaults": { "memorySearch": { "extraPaths": ["HIPPOCAMPUS_CORE.md"] } } } }
This bridges hippocampus (index.json) with OpenClaw's RAG (memory_search).
Add to your agent's session start routine:
## Every Session 1. Run `~/.openclaw/workspace/skills/hippocampus/scripts/load-core.sh`When answering context questions
Use hippocampus recall: ```bash ./scripts/recall.sh "query" ```
Track hippocampus activity over time for analytics and debugging:
# Log an encoding run ./scripts/log-event.sh encoding new=3 reinforced=2 total=157Log decay
./scripts/log-event.sh decay decayed=154 low_importance=5
Log recall
./scripts/log-event.sh recall query="user preferences" results=3
Events append to
~/.openclaw/workspace/memory/brain-events.jsonl{"ts":"2026-02-11T10:00:00Z","type":"hippocampus","event":"encoding","new":3,"reinforced":2,"total":157}
Use this for:
This skill is part of the AI Brain project — giving AI agents human-like cognitive components.
| Part | Function | Status |
|---|---|---|
| hippocampus | Memory formation, decay, reinforcement | ✅ Live |
| amygdala-memory | Emotional processing | ✅ Live |
| vta-memory | Reward and motivation | ✅ Live |
| basal-ganglia-memory | Habit formation | 🚧 Development |
| anterior-cingulate-memory | Conflict detection | 🚧 Development |
| insula-memory | Internal state awareness | 🚧 Development |
Memory is identity. Text > Brain. If you don't write it down, you lose it.
No automatic installation available. Please visit the source repository for installation instructions.
View Installation Instructions
1,500+ AI skills, agents & workflows. Install in 30 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.