> ## Documentation Index > Fetch the complete documentation index at: https://docs.memmachine.ai/llms.txt > Use this file to discover all available pages before exploring further. # Update Memory Config Endpoint > Update the episodic and/or semantic memory configuration. This endpoint allows updating the memory configuration at runtime after resources (embedders, language models, rerankers) have been added or changed. Without calling this endpoint, newly added resources will not be used by the memory systems. Both `episodic_memory` and `semantic_memory` are optional. Supply one or both depending on which sections need updating. Within each section, only the fields you supply are modified; omitted fields retain their current values. **Typical workflow:** 1. Add a new resource via `POST /config/resources/embedders` or `POST /config/resources/language_models` 2. Call this endpoint to point the memory configuration at the new resource 3. The configuration is persisted to the configuration file **Example - update episodic long-term memory to use a new embedder:** ```json { "episodic_memory": { "long_term_memory": { "embedder": "my-new-embedder" } } } ``` **Example - update semantic memory to use a new LLM and embedder:** ```json { "semantic_memory": { "llm_model": "my-new-model", "embedding_model": "my-new-embedder" } } ``` Returns 400 if no updates are supplied (both sections are null or empty). ## OpenAPI ````yaml /openapi.json put /api/v2/config/memory openapi: 3.1.0 info: title: MemMachine API version: 0.3.10 description: >- Architectural Memory Systems for AI Agents. Specialized in episodic and semantic memory management with strict namespace isolation. servers: - url: http://localhost:8080 security: [] tags: - name: Configuration description: System overview and memory subsystem configuration. - name: Episodic Configuration description: Per-project episodic memory subsystem configuration. - name: Memories description: Core operations for episodic and semantic memory ingestion and retrieval. - name: Projects description: Lifecycle management for isolated memory namespaces. - name: Resources description: Embedder, language model, and reranker lifecycle management. - name: 'Semantic Memory: Categories' description: Category, template, and tag management for semantic sets. - name: 'Semantic Memory: Features' description: Add, retrieve, and update individual semantic features. - name: 'Semantic Memory: Sets' description: Set type and set ID lifecycle, listing, and configuration. - name: System description: Infrastructure, health, and observability. paths: /api/v2/config/memory: put: tags: - Configuration summary: Update Memory Config Endpoint description: |- Update the episodic and/or semantic memory configuration. This endpoint allows updating the memory configuration at runtime after resources (embedders, language models, rerankers) have been added or changed. Without calling this endpoint, newly added resources will not be used by the memory systems. Both `episodic_memory` and `semantic_memory` are optional. Supply one or both depending on which sections need updating. Within each section, only the fields you supply are modified; omitted fields retain their current values. **Typical workflow:** 1. Add a new resource via `POST /config/resources/embedders` or `POST /config/resources/language_models` 2. Call this endpoint to point the memory configuration at the new resource 3. The configuration is persisted to the configuration file **Example - update episodic long-term memory to use a new embedder:** ```json { "episodic_memory": { "long_term_memory": { "embedder": "my-new-embedder" } } } ``` **Example - update semantic memory to use a new LLM and embedder:** ```json { "semantic_memory": { "llm_model": "my-new-model", "embedding_model": "my-new-embedder" } } ``` Returns 400 if no updates are supplied (both sections are null or empty). operationId: update_memory_config requestBody: content: application/json: schema: $ref: '#/components/schemas/UpdateMemoryConfigSpec' required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/UpdateMemoryConfigResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: UpdateMemoryConfigSpec: properties: episodic_memory: anyOf: - $ref: '#/components/schemas/UpdateEpisodicMemorySpec' - type: 'null' description: |2- Partial update for episodic memory configuration. Only supplied fields are updated; omitted fields remain unchanged. semantic_memory: anyOf: - $ref: '#/components/schemas/UpdateSemanticMemorySpec' - type: 'null' description: |2- Partial update for semantic memory configuration. Only supplied fields are updated; omitted fields remain unchanged. type: object title: UpdateMemoryConfigSpec description: Specification for updating memory configuration. UpdateMemoryConfigResponse: properties: success: type: boolean title: Success description: |2- Whether the operation succeeded. message: type: string title: Message description: |2- Status message describing the result of the operation. type: object required: - success - message title: UpdateMemoryConfigResponse description: Response model for memory configuration update. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError UpdateEpisodicMemorySpec: properties: long_term_memory: anyOf: - $ref: '#/components/schemas/UpdateLongTermMemorySpec' - type: 'null' description: |2- Partial update for long-term memory settings. Only supplied fields are updated; omitted fields remain unchanged. short_term_memory: anyOf: - $ref: '#/components/schemas/UpdateShortTermMemorySpec' - type: 'null' description: |2- Partial update for short-term memory settings. Only supplied fields are updated; omitted fields remain unchanged. long_term_memory_enabled: anyOf: - type: boolean - type: 'null' title: Long Term Memory Enabled description: |2- Whether long-term episodic memory is enabled. short_term_memory_enabled: anyOf: - type: boolean - type: 'null' title: Short Term Memory Enabled description: |2- Whether short-term episodic memory is enabled. enabled: anyOf: - type: boolean - type: 'null' title: Enabled description: |2- Whether episodic memory as a whole is enabled. type: object title: UpdateEpisodicMemorySpec description: Partial update for episodic memory configuration. UpdateSemanticMemorySpec: properties: enabled: anyOf: - type: boolean - type: 'null' title: Enabled description: |2- Whether semantic memory is enabled. When set to true, the required fields (database, llm_model, embedding_model) must also be configured. Set to false to disable semantic memory entirely. database: anyOf: - type: string - type: 'null' title: Database description: |2- The ID of the database to use for semantic memory storage. Must reference a database configured in the resources section. Used by legacy semantic storage backends. storage_backend: anyOf: - type: string - type: 'null' title: Storage Backend description: |2- The storage backend used for semantic memory. feature_store: anyOf: - type: string - type: 'null' title: Feature Store description: |2- The ID of the relational database resource used to store semantic feature data when the semantic storage backend is `vector_store`. vector_collection: anyOf: - type: string - type: 'null' title: Vector Collection description: |2- The ID of the vector store resource used to store semantic feature embeddings when the semantic storage backend is `vector_store`. vector_dimensions: anyOf: - type: integer exclusiveMinimum: 0 - type: 'null' title: Vector Dimensions description: |2- The vector dimensions used for semantic memory embeddings. If omitted for vector store storage, the configured embedder dimensions are used. llm_model: anyOf: - type: string - type: 'null' title: Llm Model description: |2- The ID of the language model to use for semantic memory extraction. Must reference a language model configured in the resources section. embedding_model: anyOf: - type: string - type: 'null' title: Embedding Model description: |2- The ID of the embedder to use for semantic memory vector search. Must reference an embedder configured in the resources section. ingestion_trigger_messages: anyOf: - type: integer exclusiveMinimum: 0 - type: 'null' title: Ingestion Trigger Messages description: |2- The number of uningested messages that triggers an ingestion cycle. ingestion_trigger_age_seconds: anyOf: - type: integer exclusiveMinimum: 0 - type: 'null' title: Ingestion Trigger Age Seconds description: |2- The maximum age (in seconds) of uningested messages before triggering an ingestion cycle. type: object title: UpdateSemanticMemorySpec description: Partial update for semantic memory configuration. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError UpdateLongTermMemorySpec: properties: backend: anyOf: - type: string enum: - declarative - event - type: 'null' title: Backend description: >- Long-term memory backend. Omit/null to keep the existing backend; set 'declarative' or 'event' to switch. embedder: anyOf: - type: string - type: 'null' title: Embedder description: |2- The ID of the embedder resource to use for long-term memory. Must reference an embedder configured in the resources section. reranker: anyOf: - type: string - type: 'null' title: Reranker description: |2- The ID of the reranker resource to use for long-term memory search. Must reference a reranker configured in the resources section. vector_graph_store: anyOf: - type: string - type: 'null' title: Vector Graph Store description: |2- The ID of the vector graph store (database) for storing long-term memories. Must reference a database configured in the resources section. vector_store: anyOf: - type: string - type: 'null' title: Vector Store description: VectorStore resource id (event backend only) segment_store: anyOf: - type: string - type: 'null' title: Segment Store description: >- SQL engine resource id backing the segment store (event backend only) properties_schema: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Properties Schema description: User-defined filterable properties (event backend only) type: object title: UpdateLongTermMemorySpec description: Partial update for long-term memory configuration. UpdateShortTermMemorySpec: properties: llm_model: anyOf: - type: string - type: 'null' title: Llm Model description: |2- The ID of the language model to use for short-term memory summarization. Must reference a language model configured in the resources section. message_capacity: anyOf: - type: integer exclusiveMinimum: 0 - type: 'null' title: Message Capacity description: |2- The maximum message capacity for short-term memory, in characters. When exceeded, older messages are summarized. type: object title: UpdateShortTermMemorySpec description: Partial update for short-term memory configuration. ````