Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.openclaw.ai/llms.txt

Use this file to discover all available pages before exploring further.

memory-lancedb is a bundled memory plugin that stores long-term memory in LanceDB and uses embeddings for recall. It can automatically recall relevant memories before a model turn and capture important facts after a response. Use it when you want a local vector database for memory, need an OpenAI-compatible embedding endpoint, or want to keep a memory database outside the default built-in memory store.
memory-lancedb is an active memory plugin. Enable it by selecting the memory slot with plugins.slots.memory = "memory-lancedb". Companion plugins such as memory-wiki can run beside it, but only one plugin owns the active memory slot.

​
Quick start

{
  plugins: {
    slots: {
      memory: "memory-lancedb",
    },
    entries: {
      "memory-lancedb": {
        enabled: true,
        config: {
          embedding: {
            provider: "openai",
            model: "text-embedding-3-small",
          },
          autoRecall: true,
          autoCapture: false,
        },
      },
    },
  },
}
Restart the Gateway after changing plugin config: 
openclaw gateway restart
Then verify the plugin is loaded: 
openclaw plugins list

​
Provider-backed embeddings

memory-lancedb can use the same memory embedding provider adapters as memory-core. Set embedding.provider and omit embedding.apiKey to use the provider’s configured auth profile, environment variable, or models.providers.<provider>.apiKey. 
{
  plugins: {
    slots: {
      memory: "memory-lancedb",
    },
    entries: {
      "memory-lancedb": {
        enabled: true,
        config: {
          embedding: {
            provider: "openai",
            model: "text-embedding-3-small",
          },
          autoRecall: true,
        },
      },
    },
  },
}
This path works with provider auth profiles that expose embedding credentials. For example, GitHub Copilot can be used when the Copilot profile/plan supports embeddings: 
{
  plugins: {
    slots: {
      memory: "memory-lancedb",
    },
    entries: {
      "memory-lancedb": {
        enabled: true,
        config: {
          embedding: {
            provider: "github-copilot",
            model: "text-embedding-3-small",
          },
        },
      },
    },
  },
}
OpenAI Codex / ChatGPT OAuth (openai-codex) is not an OpenAI Platform embeddings credential. For OpenAI embeddings, use an OpenAI API key auth profile, OPENAI_API_KEY, or models.providers.openai.apiKey. OAuth-only users can use another embedding-capable provider such as GitHub Copilot or Ollama.

​
Ollama embeddings

For Ollama embeddings, prefer the bundled Ollama embedding provider. It uses the native Ollama /api/embed endpoint and follows the same auth/base URL rules as the Ollama provider documented in Ollama. 
{
  plugins: {
    slots: {
      memory: "memory-lancedb",
    },
    entries: {
      "memory-lancedb": {
        enabled: true,
        config: {
          embedding: {
            provider: "ollama",
            baseUrl: "http://127.0.0.1:11434",
            model: "mxbai-embed-large",
            dimensions: 1024,
          },
          recallMaxChars: 400,
          autoRecall: true,
          autoCapture: false,
        },
      },
    },
  },
}
Set dimensions for non-standard embedding models. OpenClaw knows the dimensions for text-embedding-3-small and text-embedding-3-large; custom models need the value in config so LanceDB can create the vector column. For small local embedding models, lower recallMaxChars if you see context length errors from the local server.

​
OpenAI-compatible providers

Some OpenAI-compatible embedding providers reject the encoding_format parameter, while others ignore it and always return number[] vectors. memory-lancedb therefore omits encoding_format on embedding requests and accepts either float-array responses or base64-encoded float32 responses. If you have a raw OpenAI-compatible embeddings endpoint that does not have a bundled provider adapter, omit embedding.provider (or leave it as openai) and set embedding.apiKey plus embedding.baseUrl. This preserves the direct OpenAI-compatible client path. Set embedding.dimensions for providers whose model dimensions are not built in. For example, ZhiPu embedding-3 uses 2048 dimensions: 
{
  plugins: {
    entries: {
      "memory-lancedb": {
        enabled: true,
        config: {
          embedding: {
            apiKey: "${ZHIPU_API_KEY}",
            baseUrl: "https://open.bigmodel.cn/api/paas/v4",
            model: "embedding-3",
            dimensions: 2048,
          },
        },
      },
    },
  },
}

​
Recall and capture limits

memory-lancedb has two separate text limits:
SettingDefaultRangeApplies to
recallMaxChars1000100-10000text sent to the embedding API for recall
captureMaxChars500100-10000assistant message length eligible for capture
recallMaxChars controls auto-recall, the memory_recall tool, the memory_forget query path, and openclaw ltm search. Auto-recall prefers the latest user message from the turn and falls back to the full prompt only when no user message is available. This keeps channel metadata and large prompt blocks out of the embedding request. captureMaxChars controls whether a response is short enough to be considered for automatic capture. It does not cap recall query embeddings.

​
Commands

When memory-lancedb is the active memory plugin, it registers the ltm CLI namespace: 
openclaw ltm list
openclaw ltm search "project preferences"
openclaw ltm stats
The plugin also extends openclaw memory with a non-vector query subcommand that runs against the LanceDB table directly: 
openclaw memory query --cols id,text,createdAt --limit 20
openclaw memory query --filter "category = 'preference'" --order-by createdAt:desc
  • --cols <columns>: comma-separated column allowlist (defaults to id, text, importance, category, createdAt).
  • --filter <condition>: SQL-style WHERE clause; capped at 200 characters and restricted to alphanumerics, comparison operators, quotes, parentheses, and a small set of safe punctuation.
  • --limit <n>: positive integer; default 10.
  • --order-by <column>:<asc|desc>: in-memory sort applied after the filter; the sort column is auto-included in the projection.
Agents also get LanceDB memory tools from the active memory plugin:
  • memory_recall for LanceDB-backed recall
  • memory_store for saving important facts, preferences, decisions, and entities
  • memory_forget for removing matching memories

​
Storage

By default, LanceDB data lives under ~/.openclaw/memory/lancedb. Override the path with dbPath: 
{
  plugins: {
    entries: {
      "memory-lancedb": {
        enabled: true,
        config: {
          dbPath: "~/.openclaw/memory/lancedb",
          embedding: {
            apiKey: "${OPENAI_API_KEY}",
            model: "text-embedding-3-small",
          },
        },
      },
    },
  },
}
storageOptions accepts string key/value pairs for LanceDB storage backends and supports ${ENV_VAR} expansion: 
{
  plugins: {
    entries: {
      "memory-lancedb": {
        enabled: true,
        config: {
          dbPath: "s3://memory-bucket/openclaw",
          storageOptions: {
            access_key: "${AWS_ACCESS_KEY_ID}",
            secret_key: "${AWS_SECRET_ACCESS_KEY}",
            endpoint: "${AWS_ENDPOINT_URL}",
          },
          embedding: {
            apiKey: "${OPENAI_API_KEY}",
            model: "text-embedding-3-small",
          },
        },
      },
    },
  },
}

​
Runtime dependencies

memory-lancedb depends on the native @lancedb/lancedb package. Packaged OpenClaw treats that package as part of the plugin package. Gateway startup does not repair plugin dependencies; if the dependency is missing, reinstall or update the plugin package and restart the Gateway. If an older install logs a missing dist/package.json or missing @lancedb/lancedb error during plugin load, upgrade OpenClaw and restart the Gateway. If the plugin logs that LanceDB is unavailable on darwin-x64, use the default memory backend on that machine, move the Gateway to a supported platform, or disable memory-lancedb.

​
Troubleshooting

​
Input length exceeds the context length

This usually means the embedding model rejected the recall query: 
memory-lancedb: recall failed: Error: 400 the input length exceeds the context length
Set a lower recallMaxChars, then restart the Gateway: 
{
  plugins: {
    entries: {
      "memory-lancedb": {
        config: {
          recallMaxChars: 400,
        },
      },
    },
  },
}
For Ollama, also verify the embedding server is reachable from the Gateway host: 
curl http://127.0.0.1:11434/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{"model":"mxbai-embed-large","input":"hello"}'

​
Unsupported embedding model

Without dimensions, only the built-in OpenAI embedding dimensions are known. For local or custom embedding models, set embedding.dimensions to the vector size reported by that model.

​
Plugin loads but no memories appear

Check that plugins.slots.memory points at memory-lancedb, then run: 
openclaw ltm stats
openclaw ltm search "recent preference"
If autoCapture is disabled, the plugin will recall existing memories but will not automatically store new ones. Use the memory_store tool or enable autoCapture if you want automatic capture.