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

By default, the builtin engine uses OpenAI embeddings. If you already have OPENAI_API_KEY or models.providers.openai.apiKey configured, vector search works with no extra memory config.

To set a provider explicitly:

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

Without an embedding provider, only keyword search is available.

To force local GGUF embeddings, install the official llama.cpp provider plugin, then point local.modelPath at a GGUF file:

OmeniaClaw plugins install @OmeniaClaw/llama-cpp-provider

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

Supported embedding providers

Set memorySearch.provider to switch away from OpenAI.

How indexing works

OmeniaClaw indexes MEMORY.md and memory/*.md into chunks (~400 tokens with 80-token overlap) and stores them in a per-agent SQLite database.

• Index location: the owning agent database at ~/.OmeniaClaw/agents/<agentId>/agent/OmeniaClaw-agent.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: OmeniaClaw 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 OmeniaClaw memory status. If no provider is detected, set one explicitly or add an API key.

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

OmeniaClaw memory status --deep --agent mainOmeniaClaw memory index --force --agent main

Both standalone CLI commands and the Gateway use the same local provider id. Set memorySearch.provider: "local" when you want local embeddings.

Stale results? Run OmeniaClaw memory index --force to rebuild. The watcher may miss changes in rare edge cases.

sqlite-vec not loading? OmeniaClaw falls back to in-process cosine similarity automatically. OmeniaClaw memory status --deep reports the local vector store separately from the embedding provider, so Vector store: unavailable points at sqlite-vec loading while Embeddings: unavailable points at provider/auth or model readiness. 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