hippocampus – OpenClaw Skill

---

name: hippocampus description: "Background memory organ for AI agents. Runs separately from the main agent—encoding, decaying, and reinforcing memories automatically. Just like the real hippocampus in your brain. Based on Stanford Generative Agents (Park et al., 2023)." metadata: openclaw: emoji: "🧠" version: "3.7.1" author: "Community" repo: "https://github.com/ImpKind/hippocampus-skill" requires: bins: ["python3", "jq"] install: - id: "manual" kind: "manual" label: "Run install.sh" instructions: "./install.sh --with-cron"

Hippocampus Skill

"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.

Quick Start

# Install (defaults to last 100 signals)
./install.sh --with-cron

# Load 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 Options

./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

Core Concept

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.

Memory Lifecycle

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.

Memory Structure

$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

Scripts

Script	Purpose
preprocess.sh	Extract signals from conversation transcripts
encode-pipeline.sh	Score signals, prepare for LLM summarization
decay.sh	Apply 0.99^days decay to all memories
recall.sh	Search with importance weighting
load-core.sh	Output high-importance memories for session start
sync-core.sh	Generate HIPPOCAMPUS_CORE.md
consolidate.sh	Weekly review helper
reflect.sh	Self-reflection prompts
generate-dashboard.sh	Generate unified brain dashboard HTML

Brain Dashboard

Visual dashboard showing all installed brain skills:

./scripts/generate-dashboard.sh
open ~/.openclaw/workspace/brain-dashboard.html

• Auto-detects other brain skills (amygdala, VTA)
• Shows install prompts for missing skills
• Regenerates on install and cron runs
• Reads avatar/name from IDENTITY.md

After Installation (for agents)

When 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 environment variable (default: ~/.openclaw/workspace).

Importance Scoring

Initial Score (0.0-1.0)

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

Decay Formula

Based on Stanford Generative Agents (Park et al., 2023):

new_importance = importance × (0.99 ^ days_since_accessed)

• After 7 days: 93% of original
• After 30 days: 74% of original
• After 90 days: 40% of original

Semantic Reinforcement

During encoding, the LLM compares new signals to existing memories:

• Same topic? → Reinforce (bump importance ~10%, update lastAccessed)
• Truly new? → Create concise summary

This happens automatically—no manual reinforcement needed.

Thresholds

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 Schema

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"]
    }
  ]
}

Cron Jobs

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"

OpenClaw Integration

Add to memorySearch.extraPaths in openclaw.json:

{
  "agents": {
    "defaults": {
      "memorySearch": {
        "extraPaths": ["HIPPOCAMPUS_CORE.md"]
      }
    }
  }
}

This bridges hippocampus (index.json) with OpenClaw's RAG (memory_search).

Usage in AGENTS.md

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"
\`\`\`

Capture Guidelines

What Gets Captured

• User facts: Preferences, patterns, context
• Self facts: Identity, growth, opinions
• Relationship: Trust moments, shared history
• World: Projects, people, tools

Trigger Phrases (auto-scored higher)

• "Remember that..."
• "I prefer...", "I always..."
• Emotional content (struggles AND wins)
• Decisions made

AI Brain Series

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

References

• Stanford Generative Agents Paper
• GitHub: joonspk-research/generative_agents

---

Memory is identity. Text > Brain. If you don't write it down, you lose it.

🧠 Hippocampus

A living memory system for OpenClaw agents with importance scoring, time-based decay, and automatic reinforcement—just like a real brain.

The Concept

The hippocampus runs in the background, just like the real organ in your brain.

Your main agent is busy having conversations—it can't constantly stop to decide what to remember. That's what the hippocampus does. It operates as a separate process:

1. Background encoding: A cron job extracts signals, scores them, and uses LLM to create concise summaries
2. Automatic decay: Unused memories fade over time (daily cron)
3. Semantic reinforcement: When similar topics come up again, existing memories strengthen automatically

The main agent doesn't "think about" memory—it just recalls what it needs, and the hippocampus handles the rest.

Features

• Importance Scoring: Memories rated 0.0-1.0 based on signal type
• Time-Based Decay: Unused memories fade (0.99^days)
• Semantic Reinforcement: LLM detects similar topics → reinforces existing memories
• LLM Summarization: Raw messages → concise facts (via sub-agent)
• Fresh Install Friendly: Defaults to last 100 signals (not entire history)
• OpenClaw Integration: Bridges with memory_search via HIPPOCAMPUS_CORE.md

Installation

cd ~/.openclaw/workspace/skills/hippocampus
./install.sh                    # Basic (last 100 signals)
./install.sh --with-cron        # With encoding + decay cron jobs
./install.sh --signals 50       # Custom signal limit
./install.sh --whole            # Process entire history

Or via ClawdHub:

clawdhub install hippocampus

Quick Usage

# Load core memories at session start
./scripts/load-core.sh

# Search with importance weighting
./scripts/recall.sh "project deadline"

# Run encoding (usually via cron)
./scripts/encode-pipeline.sh

# Apply decay (usually via cron)
./scripts/decay.sh

Brain Dashboard

Visual dashboard showing all installed brain skills.

Access the Dashboard

Option 1: Auto-generated on install

./install.sh  # Creates brain-dashboard.html automatically

Option 2: Generate manually

./scripts/generate-dashboard.sh

Option 3: Open in browser

# macOS
open ~/.openclaw/workspace/brain-dashboard.html

# Linux
xdg-open ~/.openclaw/workspace/brain-dashboard.html

# Or open directly in browser:
# file:///home/USER/.openclaw/workspace/brain-dashboard.html

Features

• 🧠 Memory tab with stats and top memories
• 🎭 Emotions tab (if amygdala installed, or install prompt)
• ⭐ Drive tab (if VTA installed, or install prompt)
• Reads avatar/name from IDENTITY.md
• Auto-regenerates on every cron run (stays fresh)

How It Works

┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│ Preprocess  │────▶│   Score &   │────▶│   LLM       │
│  signals    │     │   Filter    │     │  Summarize  │
└─────────────┘     └─────────────┘     └──────┬──────┘
                                               │
         ┌─────────────────────────────────────┘
         │
         ▼
┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│  Semantic   │     │   Store in  │     │    Decay    │
│  Reinforce  │────▶│  index.json │◀────│ (0.99^days) │
│  OR Create  │     │             │     │             │
└─────────────┘     └─────────────┘     └─────────────┘

Memory Domains

Domain	Contents
user/	Facts about the human
self/	Agent identity & growth
relationship/	Shared context & trust
world/	External knowledge

Decay Timeline

Days Unused	Retention
7	93%
30	74%
90	40%

Cron Jobs

The encoding cron does:

1. Extract signals from conversation
2. Score by importance
3. LLM compares to existing memories (semantic matching)
4. Similar topic → Reinforce existing memory
5. New topic → Create concise summary

# Encoding every 3 hours
openclaw cron add --name hippocampus-encoding \
  --cron "0 0,3,6,9,12,15,18,21 * * *" \
  --session isolated \
  --agent-turn "Run hippocampus encoding..."

# Daily decay at 3 AM
openclaw cron add --name hippocampus-decay \
  --cron "0 3 * * *" \
  --session isolated \
  --agent-turn "Run decay.sh..."

Requirements

• Python 3
• jq
• OpenClaw

AI Brain Series

Building cognitive architecture for AI agents:

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	🚧 Coming
anterior-cingulate-memory	Conflict detection	🚧 Coming
insula-memory	Internal state awareness	🚧 Coming

Based On

Stanford Generative Agents: "Interactive Simulacra of Human Behavior" (Park et al., 2023)

License

MIT

---

Memory is identity. Text > Brain. Part of the AI Brain series.