Memory Setup

Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure memorySearch in their config. Covers MEMORY.md, daily logs, and vector search setup.

Security Scan

Instructions match the stated purpose (setting up persistent memory for Moltbot/Clawdbot) and there is no install-time code; the main issue is a small mismatch between metadata (no declared env vars) and the SKILL.md (mentions external API keys).

Purpose & Capability

The name/description (memory setup for Moltbot/Clawdbot) aligns with the instructions: editing clawdbot config, creating MEMORY.md and memory/ files, choosing an embedding provider, and restarting the gateway. All requested actions are plausible for this purpose.

Instruction Scope

SKILL.md stays on-topic: it tells the operator to add config entries, create workspace memory files, run memory_search/memory_get, and restart the gateway. It does instruct the agent/operator to create files that may contain sensitive personal data (MEMORY.md, daily logs), which is expected for a memory feature but worth noting.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, so there is no installer behavior to review and nothing is automatically written or executed by an installer.

Credentials

The registry metadata declares no required environment variables, but the SKILL.md references VOYAGE_API_KEY and OPENAI_API_KEY when using external providers. Requesting API keys is proportionate to using external embedding services, but the metadata omission is an inconsistency and the instructions access env-based credentials that were not declared.

Persistence & Privilege

The skill modifies user configuration files and asks the operator to create persistent memory files (expected). It does not request always:true or other elevated platform privileges; it does not modify other skills or system-wide settings beyond the user's own config/workspace.

Assessment

This skill appears to do what it says: help enable/configure memory for Moltbot/Clawdbot. Before installing/using it, consider the following: - API keys: SKILL.md mentions VOYAGE_API_KEY and OPENAI_API_KEY if you choose those providers, but the skill metadata does not list required env vars. Expect to supply those keys yourself if you pick an external provider. Verify the provider (Voyage) before giving it an API key. - Sensitive data: MEMORY.md and daily logs will contain persistent personal or project information. Treat them as sensitive—store them in a protected workspace, consider encryption, and avoid putting secrets or credentials in those files. - Local alternative: If privacy is a concern, use the 'local' provider option (no external API keys) as recommended in the doc. - Operational steps: The instructions include restarting the gateway (clawdbot gateway restart). That requires appropriate permissions; confirm you understand what that command does in your environment before running it. - Provenance: The skill has no homepage or source listed. If you need higher assurance, ask the publisher for source code or provenance and for the rationale behind the missing env-var declarations. Confidence is medium because this is an instruction-only skill (no code to analyze) and the only notable issue is the metadata vs. instructions mismatch about environment variables. If the publisher supplied explicit required env vars or source code, confidence could increase.

Memory Setup Skill

Transform your agent from goldfish to elephant. This skill helps configure persistent memory for Moltbot/Clawdbot.

Quick Setup

1. Enable Memory Search in Config

Add to ~/.clawdbot/clawdbot.json (or moltbot.json):

{
  "memorySearch": {
    "enabled": true,
    "provider": "voyage",
    "sources": ["memory", "sessions"],
    "indexMode": "hot",
    "minScore": 0.3,
    "maxResults": 20
  }
}

2. Create Memory Structure

In your workspace, create:

workspace/
├── MEMORY.md              # Long-term curated memory
└── memory/
    ├── logs/              # Daily logs (YYYY-MM-DD.md)
    ├── projects/          # Project-specific context
    ├── groups/            # Group chat context
    └── system/            # Preferences, setup notes

3. Initialize MEMORY.md

Create MEMORY.md in workspace root:

# MEMORY.md — Long-Term Memory

## About [User Name]
- Key facts, preferences, context

## Active Projects
- Project summaries and status

## Decisions & Lessons
- Important choices made
- Lessons learned

## Preferences
- Communication style
- Tools and workflows

Config Options Explained

Setting	Purpose	Recommended
enabled	Turn on memory search	true
provider	Embedding provider	"voyage"
sources	What to index	["memory", "sessions"]
indexMode	When to index	"hot" (real-time)
minScore	Relevance threshold	0.3 (lower = more results)
maxResults	Max snippets returned	20

Provider Options

• voyage — Voyage AI embeddings (recommended)
• openai — OpenAI embeddings
• local — Local embeddings (no API needed)

Source Options

• memory — MEMORY.md + memory/*.md files
• sessions — Past conversation transcripts
• both — Full context (recommended)

Daily Log Format

Create memory/logs/YYYY-MM-DD.md daily:

# YYYY-MM-DD — Daily Log

## [Time] — [Event/Task]
- What happened
- Decisions made
- Follow-ups needed

## [Time] — [Another Event]
- Details

Agent Instructions (AGENTS.md)

Add to your AGENTS.md for agent behavior:

## Memory Recall
Before answering questions about prior work, decisions, dates, people, preferences, or todos:
1. Run memory_search with relevant query
2. Use memory_get to pull specific lines if needed
3. If low confidence after search, say you checked

Troubleshooting

Memory search not working?

1. Check memorySearch.enabled: true in config
2. Verify MEMORY.md exists in workspace root
3. Restart gateway: clawdbot gateway restart

Results not relevant?

• Lower minScore to 0.2 for more results
• Increase maxResults to 30
• Check that memory files have meaningful content

Provider errors?

• Voyage: Set VOYAGE_API_KEY in environment
• OpenAI: Set OPENAI_API_KEY in environment
• Use local provider if no API keys available

Verification

Test memory is working:

User: "What do you remember about [past topic]?"
Agent: [Should search memory and return relevant context]

If agent has no memory, config isn't applied. Restart gateway.

Full Config Example

{
  "memorySearch": {
    "enabled": true,
    "provider": "voyage",
    "sources": ["memory", "sessions"],
    "indexMode": "hot",
    "minScore": 0.3,
    "maxResults": 20
  },
  "workspace": "/path/to/your/workspace"
}

Why This Matters

Without memory:

• Agent forgets everything between sessions
• Repeats questions, loses context
• No continuity on projects

With memory:

• Recalls past conversations
• Knows your preferences
• Tracks project history
• Builds relationship over time

Goldfish → Elephant. 🐘