OpenClaw Memory & Semantic Search

Memory in OpenClaw stores useful context that your agent can reuse later. It can include:

• Project rules
• User preferences
• Client requirements
• Previous decisions
• Workflow instructions
• Repeated task formats
• Important summaries

Example: if you tell OpenClaw, "For this client, always send short weekly updates," memory helps the agent remember that preference in future tasks. Without memory, the agent may forget instructions, repeat questions, or lose important context during long workflows. Very impressive technology, until it forgets what you said five minutes ago.

• Billing problem
• Invoice error
• Subscription failure
• Payment dispute

You may need to fix your OpenClaw memory setup if you see issues like:

• OpenClaw forgets previous messages
• Memory files are not saving
• Semantic search returns weak results
• Context overflow errors appear
• Embedding provider hits rate limits
• Memory disappears after gateway restart
• Voice messages fail when memory is enabled
• Search results are outdated or irrelevant
• Agent says old messages were compacted or forgotten

These problems usually come from configuration, storage, gateway, embedding, or context settings.

• Context overflow: prompt too large for the model
• No API key found for provider
• Memory file not found
• Semantic search failed
• Embedding provider rate limit reached
• Messages were compacted

You may also see silent problems - an empty memory folder, ignored old context, or search results that look completely unrelated. Because naturally, the worst bugs do not even introduce themselves.

openclaw gateway status openclaw --version openclaw configure --get features.memory ls -la ~/.openclaw/memory/ df -h ~/.openclaw/

openclaw configure --section memory

Set memory to enabled in your OpenClaw configuration:

{
  "features": {
    "memory": true
  }
}

openclaw gateway restart

Send this test prompt:

Remember that this OpenClaw workspace is used for customer support automation.

Then ask:

What is this OpenClaw workspace used for?

If OpenClaw recalls the saved context, basic memory is working.

• Embedding provider
• Embedding model
• API key or local endpoint
• Search result limit
• Minimum relevance score
• Chunk size
• Metadata fields
• Index location or vector database

{
  "memorySearch": {
    "enabled": true,
    "provider": "local",
    "query": {
      "maxResults": 5,
      "minScore": 0.75
    }
  }
}

openclaw gateway restart

Skip the memory setup pain.

Managed OpenClaw on Ampere.sh runs the gateway, models, storage, and embeddings so memory and semantic search work on day one - no permission errors, no vanishing context after restart.

• Start a new session: /new
• Reset the current session: /reset
• Reduce semantic search results:

{
  "memorySearch": {
    "query": {
      "maxResults": 3,
      "minScore": 0.8
    }
  }
}

• contextTokens
• maxResults
• minScore
• contextPruning
• ttl
• keepLastAssistants
• compaction

openclaw gateway status
ls -la ~/.openclaw/memory/
df -h

chmod -R u+rw ~/.openclaw/memory/
openclaw gateway restart

Reduce search result count:

{
  "memorySearch": {
    "query": {
      "maxResults": 3
    }
  }
}

Or disable semantic search temporarily:

{
  "memorySearch": {
    "enabled": false
  }
}

Then restart:

openclaw gateway restart

• Use fewer chunks
• Reduce indexing frequency
• Add retry/backoff settings
• Switch embedding provider
• Use local embeddings for testing
• Use a paid provider for production

• Chunks are too large
• Chunks are too small
• No metadata
• Old index is not updated
• Wrong embedding model
• Search result limit is too high
• Minimum relevance score is too low

• Re-index documents
• Add metadata
• Improve chunk size
• Increase minScore
• Remove outdated memory
• Separate projects or workspaces
• Test with real user queries

{
  "memorySearch": {
    "query": {
      "maxResults": 5,
      "minScore": 0.78
    }
  }
}

openclaw gateway logs --lines 200
journalctl -u openclaw --since "24 hours ago" | tail -50
dmesg | grep -i "killed process"
ls -la ~/.openclaw/memory/

• Voice message is ignored
• Transcription works but no reply appears
• Text input works but voice input fails
• Bot stops responding after voice input

Disable experimental session memory:

{
  "memorySearch": {
    "experimental": {
      "sessionMemory": false
    }
  }
}

Restart the gateway:

openclaw gateway restart

{
  "features": {
    "memory": true
  },
  "memorySearch": {
    "enabled": true,
    "provider": "local",
    "query": {
      "maxResults": 5,
      "minScore": 0.75
    },
    "experimental": {
      "sessionMemory": false
    }
  },
  "context": {
    "pruning": "cache-ttl",
    "ttl": "24h",
    "compaction": "archive"
  }
}

openclaw gateway restart

Remember that this OpenClaw workspace is used for customer support automation.

Then ask: What is this OpenClaw workspace used for?

Search previous notes for anything related to refund policy.

Use the saved project rules and summarize the next action.

• You want OpenClaw running 24/7 for real workflows
• You do not want to manage VPS setup, ports, or background services
• Your memory and semantic search setup needs stable storage
• You want fewer gateway crashes and manual restarts
• You are connecting tools like Telegram, WhatsApp, Discord, Slack, or webhooks
• You need workflows to keep running even when your local machine is off
• You want to avoid debugging embedding, memory, and file permission issues
• You are moving from testing OpenClaw to using it for actual work