Memory configuration reference

Memory configuration reference 문서는 OpenClaw 공식 문서(reference/memory-config)를 한국어로 정리한 가이드입니다. Memory search providers, retrieval modes, QMD, and multimodal indexing 명령·설정 키·코드 예시는 공식 문서를 그대로 보존하며, 해석과 절차 안내는 한국어로 제공합니다. 최종 동작은 설치된 CLI 버전과 공식 원문을 확인하세요.

핵심 요약

Memory search providers, retrieval modes, QMD, and multimodal indexing

한국어 가이드 범위: reference/memory-config 경로의 설정·명령·제약·예시를 학습용으로 재구성합니다.

문서 구성

공식 문서의 주요 섹션은 다음과 같습니다.

Remember across conversations
Provider selection
Custom provider ids
API key resolution
Remote endpoint config
Provider-specific config
Indexing behavior
Hybrid search config
Full example
Additional memory paths
Multimodal memory (Gemini)
Embedding cache
Batch indexing
Session memory search
SQLite vector acceleration (sqlite-vec)
Index storage
QMD backend config
Full QMD example
Dreaming
User settings
예제
관련 문서

상세 내용

본문

This page lists every configuration knob for OpenClaw memory search. For conceptual overviews, see:

Remember across conversations

Configure it per agent when only a trusted personal agent should use cross-conversation transcript recall:

주요 항목:

only the same agent's recognized private conversations are eligible
the conversation being answered is excluded
groups and channels are excluded as sources and destinations
unknown conversation kinds fail closed
sandboxed recall cannot use the special cross-conversation authorization

Key	Type	Default	Description
`rememberAcrossConversations`	`boolean`	On for personal installs; off with configured DM isolation	Use relevant context from this agent's other recognized private conversations.

{
  agents: {
    entries: {
      personal: {
        memory: {
          search: {
            rememberAcrossConversations: true,
          },
        },
      },
    },
  },
}

Provider selection

When provider is not set, OpenClaw uses OpenAI embeddings. Set provider explicitly to use Bedrock, DeepInfra, Gemini, GitHub Copilot, Mistral, Ollama, Voyage, a local GGUF model, or an OpenAI-compatible /v1/embeddings endpoint. Legacy configs that still say provider: "auto" resolve to openai.

Key	Type	Default	Description
`enabled`	`boolean`	`true`	Enable or disable memory search
`provider`	`string`	`"openai"`	Embedding adapter ID such as `bedrock`, `deepinfra`, `gemini`, `github-copilot`, `local`, `mistral`, `ollama`, `openai`, `openai-compatible`, or `voyage`; may also be a configured `models.providers.<id>` whose `api` points at a memory embedding adapter or OpenAI-compatible model API
`model`	`string`	provider default	Embedding model name
`fallback`	`string`	`"none"`	Fallback adapter ID when the primary fails

Custom provider ids

memory.search.provider can point at a custom models.providers. entry for memory-specific provider adapters such as ollama, or for OpenAI-compatible model APIs such as openai-responses / openai-completions. OpenClaw resolves that provider's api owner for the embedding adapter while preserving the custom provider id for endpoint, auth, and model-prefix handling. This lets multi-GPU or multi-host setups dedicate memory embeddings to a specific local endpoint:

{
  models: {
    providers: {
      "ollama-5080": {
        api: "ollama",
        baseUrl: "http://gpu-box.local:11435",
        apiKey: "ollama-local",
        models: [{ id: "qwen3-embedding:0.6b", name: "Qwen3 Embedding 0.6B" }],
      },
    },
  },
  memory: {
    search: {
      provider: "ollama-5080",
      model: "qwen3-embedding:0.6b",
    },
  },
}

API key resolution

Remote embeddings require an API key. Bedrock uses the AWS SDK default credential chain instead (instance roles, SSO, access keys, or a Bedrock API key).

Provider	Env var	Config key
Bedrock	AWS credential chain, or `AWS_BEARER_TOKEN_BEDROCK`	No API key needed
DeepInfra	`DEEPINFRA_API_KEY`	`models.providers.deepinfra.apiKey`
Gemini	`GEMINI_API_KEY`	`models.providers.google.apiKey`
GitHub Copilot	`COPILOT_GITHUB_TOKEN`, `GH_TOKEN`, `GITHUB_TOKEN`	Auth profile via device login
Mistral	`MISTRAL_API_KEY`	`models.providers.mistral.apiKey`
Ollama	`OLLAMA_API_KEY` (placeholder)	--
OpenAI	`OPENAI_API_KEY`	`models.providers.openai.apiKey`
Voyage	`VOYAGE_API_KEY`	`models.providers.voyage.apiKey`

Remote endpoint config

Use provider: "openai-compatible" for a generic OpenAI-compatible /v1/embeddings server that should not inherit global OpenAI chat credentials.

{
  memory: {
    search: {
      provider: "openai-compatible",
      model: "text-embedding-3-small",
      remote: {
        baseUrl: "https://api.example.com/v1/",
        apiKey: "YOUR_KEY",
      },
    },
  },
}

Provider-specific config

Changing model or outputDimensionality changes the index identity. OpenClaw pauses vector search until you explicitly rebuild the memory index.

{
      memory: {
        search: {
          provider: "openai-compatible",
          remote: {
            baseUrl: "https://embeddings.example/v1",
            apiKey: "${EMBEDDINGS_API_KEY}",
          },
          model: "asymmetric-embedder",
          queryInputType: "query",
          documentInputType: "passage",
        },
      },
    }

{
      memory: {
        search: {
          provider: "bedrock",
          model: "amazon.titan-embed-text-v2:0",
        },
      },
    }

{
      "Effect": "Allow",
      "Action": "bedrock:InvokeModel",
      "Resource": "*"
    }

arn:aws:bedrock:*::foundation-model/amazon.titan-embed-text-v2:0

Indexing behavior

Memory engines own synchronization, batching, watch, and post-compaction indexing heuristics. OpenClaw keeps these behaviors enabled with maintained defaults rather than exposing per-install timing switches.

Hybrid search config

Hybrid retrieval remains enabled; MMR and temporal decay remain disabled by the built-in engine policy.

Key	Type	Default	Description
`maxResults`	`number`	`6`	Max memory hits returned before injection
`minScore`	`number`	`0.35`	Minimum relevance score to include a hit

Full example

{
  memory: {
    search: {
      query: {
        maxResults: 6,
        minScore: 0.35,
      },
    },
  },
}

Additional memory paths

Paths can be absolute or workspace-relative. Directories are scanned recursively for .md files. Symlink handling depends on the active backend: the builtin engine skips symlinks, while QMD follows the underlying QMD scanner behavior.

Key	Type	Description
`extraPaths`	`string[]`	Additional directories or files to index

{
  memory: {
    search: {
      extraPaths: ["../team-docs", "/srv/shared-notes"],
    },
  },
}

Multimodal memory (Gemini)

Index images and audio alongside Markdown using Gemini Embedding 2:

Key	Type	Default	Description
`multimodal.enabled`	`boolean`	`false`	Enable multimodal indexing
`multimodal.modalities`	`string[]`	--	`["image"]`, `["audio"]`, or `["all"]`
`multimodal.maxFileBytes`	`number`	`10485760`	Max file size for indexing (10 MiB)

Embedding cache

Prevents re-embedding unchanged text during reindex or transcript updates.

Key	Type	Default	Description
`cache.enabled`	`boolean`	`true`	Cache chunk embeddings in SQLite

Batch indexing

Available for gemini, openai, and voyage. OpenAI batch is typically fastest and cheapest for large backfills.

Key	Type	Default	Description
`remote.nonBatchConcurrency`	`number`	`4`	Parallel inline embeddings
`remote.batch.enabled`	`boolean`	`false`	Enable batch embedding API

Session memory search

Index session transcripts and surface them via memory_search:

Key	Type	Default	Description
`rememberAcrossConversations`	`boolean`	`false`	Permit private cross-conversation recall
`sources`	`string[]`	`["memory"]`	Add `"sessions"` to include transcripts

{
      memory: {
        search: {
          experimental: { sessionMemory: true },
          sources: ["memory", "sessions"],
        },
      },
      tools: {
        sessions: { visibility: "agent" },
      },
    }

{
      memory: {
        backend: "qmd",
        search: {
          experimental: { sessionMemory: true },
          sources: ["memory", "sessions"],
        },
        qmd: {
          sessions: { enabled: true },
        },
      },
      tools: {
        sessions: { visibility: "agent" },
      },
    }

SQLite vector acceleration (sqlite-vec)

When sqlite-vec is unavailable, OpenClaw falls back to in-process cosine similarity automatically.

Key	Type	Default	Description
`store.vector.enabled`	`boolean`	`true`	Use sqlite-vec for vector queries
`store.vector.extensionPath`	`string`	bundled	Override sqlite-vec path

Index storage

Built-in memory indexes live in each agent's OpenClaw SQLite database at agents//agent/openclaw-agent.sqlite.

Key	Type	Default	Description
`store.fts.tokenizer`	`string`	`unicode61`	FTS5 tokenizer (`unicode61` or `trigram`)

QMD backend config

Set memory.backend = "qmd" to enable. All QMD settings live under memory.qmd:

Key	Type	Default	Description
`command`	`string`	`qmd`	QMD executable path; set an absolute path when service `PATH` differs from your shell
`searchMode`	`string`	`search`	Search command: `search`, `vsearch`, `query`
`rerank`	`boolean`	--	Set to `false` with `searchMode: "query"` and QMD 2.1+ to skip QMD reranking
`includeDefaultMemory`	`boolean`	`true`	Auto-index `MEMORY.md` + `memory/*/.md`
`paths[]`	`array`	--	Extra paths: `{ name, path, pattern? }`
`sessions.enabled`	`boolean`	`false`	Export session transcripts into QMD
`sessions.retentionDays`	`number`	--	Transcript retention
`sessions.exportDir`	`string`	--	Export directory

{
      memory: {
        qmd: {
          scope: {
            default: "deny",
            rules: [{ action: "allow", match: { chatType: "direct" } }],
          },
        },
      },
    }

Full QMD example

{
  memory: {
    backend: "qmd",
    citations: "auto",
    qmd: {
      includeDefaultMemory: true,
      update: { interval: "5m", debounceMs: 15000 },
      limits: { maxResults: 4, timeoutMs: 4000 },
      scope: {
        default: "deny",
        rules: [{ action: "allow", match: { chatType: "direct" } }],
      },
      paths: [{ name: "docs", path: "~/notes", pattern: "**/*.md" }],
    },
  },
}

Dreaming

Dreaming is configured under plugins.entries.memory-core.config.dreaming, not under memory.search.

User settings

Key	Type	Default	Description
`enabled`	`boolean`	`false`	Enable or disable dreaming entirely
`frequency`	`string`	`0 3 * * *`	Optional cron cadence for the full dreaming sweep
`model`	`string`	default model	Optional Dream Diary subagent model override
`phases.deep.maxPromotedSnippetTokens`	`number`	`160`	Maximum estimated tokens kept from each short-term recall snippet promoted into `MEMORY.md`; provenance metadata remains visible

예제

주요 항목:

Dreaming writes machine state to memory/.dreams/.
Dreaming writes human-readable narrative output to DREAMS.md (or existing dreams.md).
dreaming.model uses the existing plugin subagent trust gate; set plugins.entries.memory-core.subagent.allowModelOverride: true before enabling it.
Dream Diary retries once with the session default model when the configured model is unavailable. Trust or allowlist failures are logged and are not silently retried.
The light/deep/REM phase policy and thresholds are internal behavior, not user-facing config.

{
  plugins: {
    entries: {
      "memory-core": {
        subagent: {
          allowModelOverride: true,
          allowedModels: ["anthropic/claude-sonnet-4-6"],
        },
        config: {
          dreaming: {
            enabled: true,
            frequency: "0 3 * * *",
            model: "anthropic/claude-sonnet-4-6",
          },
        },
      },
    },
  },
}

실습 체크리스트

공식 문서와 로컬 버전을 대조합니다: https://docs.openclaw.ai/reference/memory-config
관련 CLI는 openclaw --help 및 하위 명령 --help로 옵션을 확인합니다.
설정 변경 시 openclaw config / openclaw doctor로 유효성을 검사합니다.
Gateway·채널·플러그인 변경 후에는 필요 시 Gateway를 재시작합니다.

자주 쓰는 명령·설정 예시

{
  agents: {
    entries: {
      personal: {
        memory: {
          search: {
            rememberAcrossConversations: true,
          },
        },
      },
    },
  },
}

{
  models: {
    providers: {
      "ollama-5080": {
        api: "ollama",
        baseUrl: "http://gpu-box.local:11435",
        apiKey: "ollama-local",
        models: [{ id: "qwen3-embedding:0.6b", name: "Qwen3 Embedding 0.6B" }],
      },
    },
  },
  memory: {
    search: {
      provider: "ollama-5080",
      model: "qwen3-embedding:0.6b",
    },
  },
}

{
  memory: {
    search: {
      provider: "openai-compatible",
      model: "text-embedding-3-small",
      remote: {
        baseUrl: "https://api.example.com/v1/",
        apiKey: "YOUR_KEY",
      },
    },
  },
}

{
      memory: {
        search: {
          provider: "openai-compatible",
          remote: {
            baseUrl: "https://embeddings.example/v1",
            apiKey: "${EMBEDDINGS_API_KEY}",
          },
          model: "asymmetric-embedder",
          queryInputType: "query",
          documentInputType: "passage",
        },
      },
    }

{
      memory: {
        search: {
          provider: "bedrock",
          model: "amazon.titan-embed-text-v2:0",
        },
      },
    }

{
      "Effect": "Allow",
      "Action": "bedrock:InvokeModel",
      "Resource": "*"
    }

Memory configuration reference

핵심 요약

Memory search providers, retrieval modes, QMD, and multimodal indexing

한국어 가이드 범위: reference/memory-config 경로의 설정·명령·제약·예시를 학습용으로 재구성합니다.

문서 구성

공식 문서의 주요 섹션은 다음과 같습니다.

Remember across conversations
Provider selection
Custom provider ids
API key resolution
Remote endpoint config
Provider-specific config
Indexing behavior
Hybrid search config
Full example
Additional memory paths
Multimodal memory (Gemini)
Embedding cache
Batch indexing
Session memory search
SQLite vector acceleration (sqlite-vec)
Index storage
QMD backend config
Full QMD example
Dreaming
User settings
예제
관련 문서

상세 내용

본문

This page lists every configuration knob for OpenClaw memory search. For conceptual overviews, see:

Remember across conversations

Configure it per agent when only a trusted personal agent should use cross-conversation transcript recall:

주요 항목:

only the same agent's recognized private conversations are eligible
the conversation being answered is excluded
groups and channels are excluded as sources and destinations
unknown conversation kinds fail closed
sandboxed recall cannot use the special cross-conversation authorization

Key	Type	Default	Description
`rememberAcrossConversations`	`boolean`	On for personal installs; off with configured DM isolation	Use relevant context from this agent's other recognized private conversations.

{
  agents: {
    entries: {
      personal: {
        memory: {
          search: {
            rememberAcrossConversations: true,
          },
        },
      },
    },
  },
}

Provider selection

Key	Type	Default	Description
`enabled`	`boolean`	`true`	Enable or disable memory search
`provider`	`string`	`"openai"`	Embedding adapter ID such as `bedrock`, `deepinfra`, `gemini`, `github-copilot`, `local`, `mistral`, `ollama`, `openai`, `openai-compatible`, or `voyage`; may also be a configured `models.providers.<id>` whose `api` points at a memory embedding adapter or OpenAI-compatible model API
`model`	`string`	provider default	Embedding model name
`fallback`	`string`	`"none"`	Fallback adapter ID when the primary fails

Custom provider ids

{
  models: {
    providers: {
      "ollama-5080": {
        api: "ollama",
        baseUrl: "http://gpu-box.local:11435",
        apiKey: "ollama-local",
        models: [{ id: "qwen3-embedding:0.6b", name: "Qwen3 Embedding 0.6B" }],
      },
    },
  },
  memory: {
    search: {
      provider: "ollama-5080",
      model: "qwen3-embedding:0.6b",
    },
  },
}

API key resolution

Remote embeddings require an API key. Bedrock uses the AWS SDK default credential chain instead (instance roles, SSO, access keys, or a Bedrock API key).

Provider	Env var	Config key
Bedrock	AWS credential chain, or `AWS_BEARER_TOKEN_BEDROCK`	No API key needed
DeepInfra	`DEEPINFRA_API_KEY`	`models.providers.deepinfra.apiKey`
Gemini	`GEMINI_API_KEY`	`models.providers.google.apiKey`
GitHub Copilot	`COPILOT_GITHUB_TOKEN`, `GH_TOKEN`, `GITHUB_TOKEN`	Auth profile via device login
Mistral	`MISTRAL_API_KEY`	`models.providers.mistral.apiKey`
Ollama	`OLLAMA_API_KEY` (placeholder)	--
OpenAI	`OPENAI_API_KEY`	`models.providers.openai.apiKey`
Voyage	`VOYAGE_API_KEY`	`models.providers.voyage.apiKey`

Remote endpoint config

Use provider: "openai-compatible" for a generic OpenAI-compatible /v1/embeddings server that should not inherit global OpenAI chat credentials.

{
  memory: {
    search: {
      provider: "openai-compatible",
      model: "text-embedding-3-small",
      remote: {
        baseUrl: "https://api.example.com/v1/",
        apiKey: "YOUR_KEY",
      },
    },
  },
}

Provider-specific config

Changing model or outputDimensionality changes the index identity. OpenClaw pauses vector search until you explicitly rebuild the memory index.

{
      memory: {
        search: {
          provider: "openai-compatible",
          remote: {
            baseUrl: "https://embeddings.example/v1",
            apiKey: "${EMBEDDINGS_API_KEY}",
          },
          model: "asymmetric-embedder",
          queryInputType: "query",
          documentInputType: "passage",
        },
      },
    }

{
      memory: {
        search: {
          provider: "bedrock",
          model: "amazon.titan-embed-text-v2:0",
        },
      },
    }

{
      "Effect": "Allow",
      "Action": "bedrock:InvokeModel",
      "Resource": "*"
    }

arn:aws:bedrock:*::foundation-model/amazon.titan-embed-text-v2:0

Indexing behavior

Hybrid search config

Hybrid retrieval remains enabled; MMR and temporal decay remain disabled by the built-in engine policy.

Key	Type	Default	Description
`maxResults`	`number`	`6`	Max memory hits returned before injection
`minScore`	`number`	`0.35`	Minimum relevance score to include a hit

Full example

{
  memory: {
    search: {
      query: {
        maxResults: 6,
        minScore: 0.35,
      },
    },
  },
}

Additional memory paths

Key	Type	Description
`extraPaths`	`string[]`	Additional directories or files to index

{
  memory: {
    search: {
      extraPaths: ["../team-docs", "/srv/shared-notes"],
    },
  },
}

Multimodal memory (Gemini)

Index images and audio alongside Markdown using Gemini Embedding 2:

Key	Type	Default	Description
`multimodal.enabled`	`boolean`	`false`	Enable multimodal indexing
`multimodal.modalities`	`string[]`	--	`["image"]`, `["audio"]`, or `["all"]`
`multimodal.maxFileBytes`	`number`	`10485760`	Max file size for indexing (10 MiB)

Embedding cache

Prevents re-embedding unchanged text during reindex or transcript updates.

Key	Type	Default	Description
`cache.enabled`	`boolean`	`true`	Cache chunk embeddings in SQLite

Batch indexing

Available for gemini, openai, and voyage. OpenAI batch is typically fastest and cheapest for large backfills.

Key	Type	Default	Description
`remote.nonBatchConcurrency`	`number`	`4`	Parallel inline embeddings
`remote.batch.enabled`	`boolean`	`false`	Enable batch embedding API

Session memory search

Index session transcripts and surface them via memory_search:

Key	Type	Default	Description
`rememberAcrossConversations`	`boolean`	`false`	Permit private cross-conversation recall
`sources`	`string[]`	`["memory"]`	Add `"sessions"` to include transcripts

{
      memory: {
        search: {
          experimental: { sessionMemory: true },
          sources: ["memory", "sessions"],
        },
      },
      tools: {
        sessions: { visibility: "agent" },
      },
    }

{
      memory: {
        backend: "qmd",
        search: {
          experimental: { sessionMemory: true },
          sources: ["memory", "sessions"],
        },
        qmd: {
          sessions: { enabled: true },
        },
      },
      tools: {
        sessions: { visibility: "agent" },
      },
    }

SQLite vector acceleration (sqlite-vec)

When sqlite-vec is unavailable, OpenClaw falls back to in-process cosine similarity automatically.

Key	Type	Default	Description
`store.vector.enabled`	`boolean`	`true`	Use sqlite-vec for vector queries
`store.vector.extensionPath`	`string`	bundled	Override sqlite-vec path

Index storage

Built-in memory indexes live in each agent's OpenClaw SQLite database at agents//agent/openclaw-agent.sqlite.

Key	Type	Default	Description
`store.fts.tokenizer`	`string`	`unicode61`	FTS5 tokenizer (`unicode61` or `trigram`)

QMD backend config

Set memory.backend = "qmd" to enable. All QMD settings live under memory.qmd:

Key	Type	Default	Description
`command`	`string`	`qmd`	QMD executable path; set an absolute path when service `PATH` differs from your shell
`searchMode`	`string`	`search`	Search command: `search`, `vsearch`, `query`
`rerank`	`boolean`	--	Set to `false` with `searchMode: "query"` and QMD 2.1+ to skip QMD reranking
`includeDefaultMemory`	`boolean`	`true`	Auto-index `MEMORY.md` + `memory/*/.md`
`paths[]`	`array`	--	Extra paths: `{ name, path, pattern? }`
`sessions.enabled`	`boolean`	`false`	Export session transcripts into QMD
`sessions.retentionDays`	`number`	--	Transcript retention
`sessions.exportDir`	`string`	--	Export directory

{
      memory: {
        qmd: {
          scope: {
            default: "deny",
            rules: [{ action: "allow", match: { chatType: "direct" } }],
          },
        },
      },
    }

Full QMD example

{
  memory: {
    backend: "qmd",
    citations: "auto",
    qmd: {
      includeDefaultMemory: true,
      update: { interval: "5m", debounceMs: 15000 },
      limits: { maxResults: 4, timeoutMs: 4000 },
      scope: {
        default: "deny",
        rules: [{ action: "allow", match: { chatType: "direct" } }],
      },
      paths: [{ name: "docs", path: "~/notes", pattern: "**/*.md" }],
    },
  },
}

Dreaming

Dreaming is configured under plugins.entries.memory-core.config.dreaming, not under memory.search.

User settings

Key	Type	Default	Description
`enabled`	`boolean`	`false`	Enable or disable dreaming entirely
`frequency`	`string`	`0 3 * * *`	Optional cron cadence for the full dreaming sweep
`model`	`string`	default model	Optional Dream Diary subagent model override
`phases.deep.maxPromotedSnippetTokens`	`number`	`160`	Maximum estimated tokens kept from each short-term recall snippet promoted into `MEMORY.md`; provenance metadata remains visible

예제

주요 항목:

Dreaming writes machine state to memory/.dreams/.
Dreaming writes human-readable narrative output to DREAMS.md (or existing dreams.md).
dreaming.model uses the existing plugin subagent trust gate; set plugins.entries.memory-core.subagent.allowModelOverride: true before enabling it.
Dream Diary retries once with the session default model when the configured model is unavailable. Trust or allowlist failures are logged and are not silently retried.
The light/deep/REM phase policy and thresholds are internal behavior, not user-facing config.

{
  plugins: {
    entries: {
      "memory-core": {
        subagent: {
          allowModelOverride: true,
          allowedModels: ["anthropic/claude-sonnet-4-6"],
        },
        config: {
          dreaming: {
            enabled: true,
            frequency: "0 3 * * *",
            model: "anthropic/claude-sonnet-4-6",
          },
        },
      },
    },
  },
}

실습 체크리스트

공식 문서와 로컬 버전을 대조합니다: https://docs.openclaw.ai/reference/memory-config
관련 CLI는 openclaw --help 및 하위 명령 --help로 옵션을 확인합니다.
설정 변경 시 openclaw config / openclaw doctor로 유효성을 검사합니다.
Gateway·채널·플러그인 변경 후에는 필요 시 Gateway를 재시작합니다.

자주 쓰는 명령·설정 예시

{
  agents: {
    entries: {
      personal: {
        memory: {
          search: {
            rememberAcrossConversations: true,
          },
        },
      },
    },
  },
}

{
  models: {
    providers: {
      "ollama-5080": {
        api: "ollama",
        baseUrl: "http://gpu-box.local:11435",
        apiKey: "ollama-local",
        models: [{ id: "qwen3-embedding:0.6b", name: "Qwen3 Embedding 0.6B" }],
      },
    },
  },
  memory: {
    search: {
      provider: "ollama-5080",
      model: "qwen3-embedding:0.6b",
    },
  },
}

{
  memory: {
    search: {
      provider: "openai-compatible",
      model: "text-embedding-3-small",
      remote: {
        baseUrl: "https://api.example.com/v1/",
        apiKey: "YOUR_KEY",
      },
    },
  },
}

{
      memory: {
        search: {
          provider: "openai-compatible",
          remote: {
            baseUrl: "https://embeddings.example/v1",
            apiKey: "${EMBEDDINGS_API_KEY}",
          },
          model: "asymmetric-embedder",
          queryInputType: "query",
          documentInputType: "passage",
        },
      },
    }

{
      memory: {
        search: {
          provider: "bedrock",
          model: "amazon.titan-embed-text-v2:0",
        },
      },
    }

{
      "Effect": "Allow",
      "Action": "bedrock:InvokeModel",
      "Resource": "*"
    }

Memory configuration reference

핵심 요약

문서 구성

상세 내용

본문

Remember across conversations

Provider selection

Custom provider ids

API key resolution

Remote endpoint config

Provider-specific config

Indexing behavior

Hybrid search config

Full example

Additional memory paths

Multimodal memory (Gemini)

Embedding cache

Batch indexing

Session memory search

SQLite vector acceleration (sqlite-vec)

Index storage

QMD backend config

Full QMD example

Dreaming

User settings

예제

관련 문서

실습 체크리스트

자주 쓰는 명령·설정 예시

관련 링크

관련 가이드

Memory configuration reference

핵심 요약

문서 구성

상세 내용

본문

Remember across conversations

Provider selection

Custom provider ids

API key resolution

Remote endpoint config

Provider-specific config

Indexing behavior

Hybrid search config

Full example

Additional memory paths

Multimodal memory (Gemini)

Embedding cache

Batch indexing

Session memory search

SQLite vector acceleration (sqlite-vec)

Index storage

QMD backend config

Full QMD example

Dreaming

User settings

예제

관련 문서

실습 체크리스트

자주 쓰는 명령·설정 예시

관련 링크

관련 가이드