memory-setup
4
总安装量
3
周安装量
#51603
全站排名
安装命令
npx skills add https://github.com/sundial-org/awesome-openclaw-skills --skill memory-setup
Agent 安装分布
openclaw
3
github-copilot
3
codex
3
kimi-cli
3
gemini-cli
3
cursor
3
Skill 文档
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/
âââ MEMORY.md # Long-term curated memory
âââ memory/
âââ logs/ # Daily logs (YYYY-MM-DD.md)
âââ projects/ # Project-specific context
âââ groups/ # Group chat context
âââ system/ # Preferences, setup notes
3. Initialize MEMORY.md
Create MEMORY.md in workspace root:
# MEMORY.md â 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
voyageâ Voyage AI embeddings (recommended)openaiâ OpenAI embeddingslocalâ Local embeddings (no API needed)
Source Options
memoryâ MEMORY.md + memory/*.md filessessionsâ Past conversation transcriptsbothâ Full context (recommended)
Daily Log Format
Create memory/logs/YYYY-MM-DD.md daily:
# YYYY-MM-DD â Daily Log
## [Time] â [Event/Task]
- What happened
- Decisions made
- Follow-ups needed
## [Time] â [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?
- Check
memorySearch.enabled: truein config - Verify MEMORY.md exists in workspace root
- Restart gateway:
clawdbot gateway restart
Results not relevant?
- Lower
minScoreto0.2for more results - Increase
maxResultsto30 - Check that memory files have meaningful content
Provider errors?
- Voyage: Set
VOYAGE_API_KEYin environment - OpenAI: Set
OPENAI_API_KEYin environment - Use
localprovider 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 â Elephant. ð