Chen Memory Setup

Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure m...

Security Scan

The skill's instructions match its stated purpose of configuring persistent memory, but there are inconsistencies (undeclared API keys mentioned in the docs and a metadata owner-id mismatch) and privacy/operational risks (indexing session transcripts, editing user config, restarting the gateway) you should be aware of before installing.

Purpose & Capability

The name/description align with the SKILL.md: it configures memorySearch, MEMORY.md, and memory/ logs — all expected. However, the documentation references setting VOYAGE_API_KEY and OPENAI_API_KEY although the skill's declared requirements list no environment variables; additionally the registry ownerId differs from the _meta.json ownerId, which suggests a packaging/metadata inconsistency that merits verification.

Instruction Scope

The instructions are narrowly scoped to editing ~/.clawdbot/clawdbot.json (or moltbot.json), creating workspace memory files, and restarting the gateway. Those actions are coherent with enabling memory. Important privacy/operational implications: it recommends indexing 'sessions' (past conversation transcripts) which can expose sensitive data to the memory index and any embedding provider, and it instructs restarting the gateway via 'clawdbot gateway restart' which performs an operational action that should be run intentionally by the user.

Install Mechanism

No install spec or code files — instruction-only — so nothing will be downloaded or written to disk by an installer step. This is the lowest install-surface risk.

Credentials

The notes tell users to set VOYAGE_API_KEY and OPENAI_API_KEY for provider errors, but the skill metadata does not declare any required environment variables or a primary credential. That mismatch reduces transparency. Requiring embedding API keys would be proportionate to the task, but they should be declared in the skill manifest so users know up-front what secrets are needed.

Persistence & Privilege

always:false (not force-included) and no persistent install actions are requested. However, the instructions explicitly direct editing agent config files and restarting the gateway; if you allow autonomous agent actions, the agent could apply these changes without further manual approval. Consider whether the agent has permission to modify those files or restart services in your environment.

What to consider before installing

This skill appears to do what it says (configure memory) but check a few things before proceeding: 1) Verify the publisher/owner — the registry ownerId and _meta.json ownerId differ, which could indicate a copy/paste or repackaging; confirm you trust the source. 2) Back up your existing ~/.clawdbot/clawdbot.json and workspace before making changes. 3) Be cautious about enabling 'sources: ["sessions"]' — that will index past conversation transcripts and can surface sensitive data to whichever embedding provider you choose. 4) Only provide VOYAGE_API_KEY or OPENAI_API_KEY to trusted providers and understand how those providers store/process embeddings. 5) If you allow the agent to act autonomously, be aware it could modify config and restart the gateway; if you want manual control, don't grant autonomous execution or run the suggested commands yourself. 6) If anything looks unfamiliar (owner mismatch, unexpected workspace paths, unfamiliar provider names), ask the publisher for clarification before installing.

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. 🐘