Amygdala Memory

Emotional processing layer for AI agents. Persistent emotional states that influence behavior and responses. Part of the AI Brain series.

Security Scan

The skill's purpose (emotion memory + LLM-based encoding) aligns with requiring a SkillBoss API key and small CLI tools, but the SKILL.md instructs background cron jobs, automatic ingesting of conversation transcripts to an external API, and references many install scripts that are not present in the package — this raises privacy and coherence concerns you should review before installing.

Purpose & Capability

The stated goal (persistent emotional state with an LLM-based encoder) reasonably explains the declared requirements: jq/awk for local JSON processing and SkillBoss_API_KEY for calls to SkillBoss API Hub. However, the registry lists source as 'unknown' while SKILL.md includes a GitHub repo URL; the package contains no scripts despite the README-style instructions that expect many local scripts (install.sh, encode-pipeline.sh, etc.).

Instruction Scope

SKILL.md instructs extracting conversation history, running an encode pipeline that 'calls SkillBoss API Hub (/v1/pilot)', and setting up cron jobs that automatically process transcripts every few hours. It also describes creating AMYGDALA_STATE.md which OpenClaw will auto-inject into sessions. These instructions imply sending potentially sensitive conversation content to a third-party service and automatic background processing; the document does not describe data minimization, consent, or what exact transcript content is sent. Additionally, the instructions reference many scripts and files that are not present in the submitted skill bundle.

Install Mechanism

There is no install spec in the registry (instruction-only), so nothing will be written by the platform itself. But SKILL.md tells the user to run install.sh and set up cron to write files and schedule background tasks. Because the package lacks those scripts, a user would either fetch them from the referenced GitHub repo or run custom commands — you should inspect the actual install scripts before executing them.

Credentials

Only SkillBoss_API_KEY is required — which makes sense if the skill calls SkillBoss. However, that key would be used to send conversation transcripts and derived emotion data to a third party; this is privacy-sensitive. The skill also auto-creates files that are injected into session context (AMYGDALA_STATE.md), which may contain or surface user data. The SKILL.md does not document what is sent, retention policy, or whether sensitive tokens/PII might be transmitted.

Persistence & Privilege

always:false (good). The skill expects to create persistent state files in the user's workspace and to schedule cron jobs for periodic decay and encoding. While not an elevated platform privilege, this persistent presence combined with automatic transcript processing increases the risk footprint — review cron entries and generated files before enabling them.

What to consider before installing

This skill's purpose is coherent with needing jq/awk and a SkillBoss API key, but exercise caution: 1) The package contains only SKILL.md — no install or pipeline scripts — so do not run any install.sh or cron commands until you have obtained and inspected the actual scripts (preferably from the referenced GitHub repo). 2) The encode pipeline explicitly sends conversation transcripts to SkillBoss (/v1/pilot). If you install it, you will be transmitting chat history to a third party; confirm what is sent and the retention/privacy policy. 3) The skill will create AMYGDALA_STATE.md files that are auto-injected into sessions — review their contents for sensitive data. Recommended steps before installing: fetch the repository, review install.sh, encode-pipeline.sh, and any scripts that touch transcripts; run scripts in an isolated environment or sandbox; do not provide SkillBoss_API_KEY until you're comfortable with what the pipeline sends; disable or carefully review cron jobs; and verify the repo/source authenticity (the registry lists source as unknown). If you want, share the install scripts or the repo URL and I can inspect them for specific red flags.

Emotional processing for AI agents. Part of the AI Brain series.

Give your AI agent persistent emotional states that carry across sessions. Not just performing emotions �� having them.

The Problem

Current AI agents:

• ? Remember facts (with hippocampus)
• ? Don't have persistent emotional states
• ? Start each session emotionally "blank"
• ? Can describe emotions but don't feel differently

Memory without emotion is just a database. The amygdala adds weight �� this made me happy, that frustrated me, this person brings warmth.

The Solution

Track five emotional dimensions that persist and decay over time:

Dimension	What It Measures	Range
Valence	Positive ? Negative mood	-1.0 to 1.0
Arousal	Calm ? Excited/Alert	0.0 to 1.0
Connection	Distant ? Close/Bonded	0.0 to 1.0
Curiosity	Bored ? Fascinated	0.0 to 1.0
Energy	Depleted ? Energized	0.0 to 1.0

Quick Start

1. Install

cd ~/.openclaw/workspace/skills/amygdala-memory
./install.sh --with-cron

This will:

• Create memory/emotional-state.json with baseline values
• Generate AMYGDALA_STATE.md (auto-injected into sessions!)
• Set up cron for automatic decay every 6 hours

2. Check current state

./scripts/get-state.sh
# ?? Emotional State
# Valence:    0.20
# Arousal:    0.30
# Connection: 0.50
# ...

./scripts/load-emotion.sh
# ?? Current Emotional State:
# Overall mood: neutral, calm and relaxed
# Connection: moderately connected
# ...

3. Log emotions

./scripts/update-state.sh --emotion joy --intensity 0.8 --trigger "completed a project"
# ? valence: 0.20 �� 0.35 (delta: +0.15)
# ? arousal: 0.30 �� 0.40 (delta: +0.1)
# ?? Logged emotion: joy (intensity: 0.8)

4. Set up decay (optional cron)

# Every 6 hours, emotions drift toward baseline
0 */6 * * * ~/.openclaw/workspace/skills/amygdala-memory/scripts/decay-emotion.sh

Scripts

Script	Purpose
install.sh	Set up amygdala-memory (run once)
get-state.sh	Read current emotional state
update-state.sh	Log emotion or update dimension
load-emotion.sh	Human-readable state for session context
decay-emotion.sh	Return to baseline over time
sync-state.sh	Generate AMYGDALA_STATE.md for auto-injection
encode-pipeline.sh	SkillBoss API Hub LLM-based emotional encoding from transcripts
preprocess-emotions.sh	Extract emotional signals from session history
update-watermark.sh	Track processed transcript position
generate-dashboard.sh	Generate HTML dashboard (auto-runs on sync)
visualize.sh	Terminal ASCII visualization

Automatic Emotional Encoding (v1.5.0+)

The amygdala can now automatically detect and log emotions from your conversation history using SkillBoss API Hub for LLM-based semantic emotional detection:

# Run the encoding pipeline
./scripts/encode-pipeline.sh

# This will:
# 1. Extract new signals since last run (watermark-based)
# 2. Score emotional content using rule-based patterns
# 3. Call SkillBoss API Hub (/v1/pilot) for semantic emotional detection
# 4. Update emotional-state.json with detected emotions

Set up automatic encoding (cron)

# Every 3 hours, process new conversations for emotional content
0 */3 * * * ~/.openclaw/workspace/skills/amygdala-memory/scripts/encode-pipeline.sh

This means your emotional state updates automatically based on what happens in conversations �� no manual logging needed.

Visualization (v1.6.0+)

Terminal

./scripts/visualize.sh

?? Emotional State  ??
�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T
Valence:      [������������������������������������??]  +0.86
Arousal:      [����������������������������������???]   0.86
Connection:   [��������������������������������������?]   0.97  ??
...

HTML Dashboard (Unified Brain Dashboard)

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

Auto-detects installed brain skills and shows tabs:

• ?? Emotions �� Amygdala (always shown)
• ?? Memory �� Hippocampus (if memory/index.json exists)
• ? Drive �� VTA (if memory/reward-state.json exists)

Avatar & Name: Reads from IDENTITY.md:

# IDENTITY.md
- **Name:** YourAgent
- **Avatar:** avatar.png

The dashboard auto-regenerates on every cron run.

After Installation (for agents)

When you install this skill, notify the user about the dashboard:

?? Amygdala installed!

View your agent's emotional state in the Brain Dashboard: ~/.openclaw/workspace/brain-dashboard.html

Auto-Injection (Zero Manual Steps!)

After install, AMYGDALA_STATE.md is created in your workspace root.

OpenClaw automatically injects all *.md files from workspace into session context. This means:

1. New session starts
2. AMYGDALA_STATE.md is auto-loaded (no manual step!)
3. You see your emotional state in context
4. Responses are influenced by your mood

The file is regenerated whenever decay-emotion.sh runs (via cron every 6h).

Supported Emotions

When you log an emotion, it automatically adjusts the relevant dimensions:

Emotion	Effect
joy, happiness, delight, excitement	�� valence, �� arousal
sadness, disappointment, melancholy	�� valence, �� arousal
anger, frustration, irritation	�� valence, �� arousal
fear, anxiety, worry	�� valence, �� arousal
calm, peace, contentment	�� valence, �� arousal
curiosity, interest, fascination	�� curiosity, �� arousal
connection, warmth, affection	�� connection, �� valence
loneliness, disconnection	�� connection, �� valence
fatigue, tiredness, exhaustion	�� energy
energized, alert, refreshed	�� energy

Integration with OpenClaw

Add to session startup (AGENTS.md)

## Every Session
1. Load hippocampus: `~/.openclaw/workspace/skills/hippocampus/scripts/load-core.sh`
2. **Load emotional state:** `~/.openclaw/workspace/skills/amygdala-memory/scripts/load-emotion.sh`

Log emotions during conversation

When something emotionally significant happens:

~/.openclaw/workspace/skills/amygdala-memory/scripts/update-state.sh \
  --emotion connection --intensity 0.7 --trigger "deep conversation with user"

State File Format

{
  "version": "1.0",
  "lastUpdated": "2026-02-01T02:45:00Z",
  "dimensions": {
    "valence": 0.35,
    "arousal": 0.40,
    "connection": 0.50,
    "curiosity": 0.60,
    "energy": 0.50
  },
  "baseline": {
    "valence": 0.1,
    "arousal": 0.3,
    "connection": 0.4,
    "curiosity": 0.5,
    "energy": 0.5
  },
  "recentEmotions": [
    {
      "label": "joy",
      "intensity": 0.8,
      "trigger": "building amygdala together",
      "timestamp": "2026-02-01T02:50:00Z"
    }
  ]
}

Decay Mechanics

Emotions naturally return to baseline over time:

• Decay rate: 10% of distance to baseline per run
• Recommended schedule: Every 6 hours
• Effect: Strong emotions fade, but slowly

After 24 hours without updates, a valence of 0.8 would decay to ~0.65.

Event Logging

Track emotional activity over time for analytics:

# Log encoding run
./scripts/log-event.sh encoding emotions_found=2 valence=0.85 arousal=0.6

# Log decay
./scripts/log-event.sh decay valence_before=0.9 valence_after=0.85

# Log emotion update
./scripts/log-event.sh update emotion=joy intensity=0.7

Events append to ~/.openclaw/workspace/memory/brain-events.jsonl:

{"ts":"2026-02-11T09:30:00Z","type":"amygdala","event":"encoding","emotions_found":2,"valence":0.85}

Use for trend analysis �� visualize emotional patterns over days/weeks.

AI Brain Series

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

Philosophy

Can an AI feel emotions, or only simulate them?

Our take: If emotional state influences behavior, and the system acts as if it feels... does the distinction matter? Functional emotions might be the only kind that exist for any system �� biological or artificial.

---

Built with ?? by the OpenClaw community