Builtin memory engine

The builtin engine is the default memory backend. It stores your memory index in a per-agent SQLite database and needs no extra dependencies to get started.

What it provides

• Keyword search via FTS5 full-text indexing (BM25 scoring).
• Vector search via embeddings from any supported provider.
• Hybrid search that combines both for best results.
• CJK support via trigram tokenization for Chinese, Japanese, and Korean.
• sqlite-vec acceleration for in-database vector queries (optional).

Getting started

If you have an API key for OpenAI, Gemini, Voyage, Mistral, or DeepInfra, the builtin engine auto-detects it and enables vector search. No config needed.

To set a provider explicitly:

json5
Copy
{
  agents: {
    defaults: {
      memorySearch: {
        provider: "openai",
      },
    },
  },
}

Without an embedding provider, only keyword search is available.

To force the built-in local embedding provider, install the optional

runtime package next to OpenClaw, then point at a GGUF file:

json5
Copy
{
  agents: {
    defaults: {
      memorySearch: {
        provider: "local",
        fallback: "none",
        local: {
          modelPath: "~/.node-llama-cpp/models/embeddinggemma-300m-qat-Q8_0.gguf",
        },
      },
    },
  },
}

Supported embedding providers

Auto-detection picks the first provider whose API key can be resolved, in the order shown. Set

to override.

How indexing works

OpenClaw indexes

and into chunks (~400 tokens with 80-token overlap) and stores them in a per-agent SQLite database.

• Index location:
  text

  Copy

  ~/.openclaw/memory/<agentId>.sqlite
• Storage maintenance: SQLite WAL sidecars are bounded with periodic and shutdown checkpoints.
• File watching: changes to memory files trigger a debounced reindex (1.5s).
• Auto-reindex: when the embedding provider, model, or chunking config changes, the entire index is rebuilt automatically.
• Reindex on demand:
  text

  Copy

  openclaw memory index --force

When to use

The builtin engine is the right choice for most users:

• Works out of the box with no extra dependencies.
• Handles keyword and vector search well.
• Supports all embedding providers.
• Hybrid search combines the best of both retrieval approaches.

Consider switching to QMD if you need reranking, query expansion, or want to index directories outside the workspace.

Consider Honcho if you want cross-session memory with automatic user modeling.

Troubleshooting

Memory search disabled? Check

. If no provider is detected, set one explicitly or add an API key.

Local provider not detected? Confirm the local path exists and run:

bash
Copy
openclaw memory status --deep --agent main
openclaw memory index --force --agent main

Both standalone CLI commands and the Gateway use the same

provider id. If the provider is set to , local embeddings are considered first only when points to an existing local file.

Stale results? Run

to rebuild. The watcher may miss changes in rare edge cases.

sqlite-vec not loading? OpenClaw falls back to in-process cosine similarity automatically. Check logs for the specific load error.

Configuration

For embedding provider setup, hybrid search tuning (weights, MMR, temporal decay), batch indexing, multimodal memory, sqlite-vec, extra paths, and all other config knobs, see the Memory configuration reference.

Related

• Memory overview
• Memory search
• Active memory