> ## 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. # Add Memories > Add memory messages to a project. The `types` field in the request specifies which memory types to add to: - If `types` is empty or not provided, memories are added to all types (episodic and semantic) - If `types` only contains `"episodic"`, memories are added only to Episodic memory - If `types` only contains `"semantic"`, memories are added only to Semantic memory - If `types` contains both, memories are added to both types Each memory message represents a discrete piece of information to be stored in the project's memory system. Messages can include content, metadata, timestamps, and other contextual details. The producer field indicates who created the message, while the produced_for field specifies the intended recipient. These fields help provide context for the memory and if provided should be user-friendly names. The endpoint accepts a batch of messages to be added in a single request. ## OpenAPI ````yaml /openapi.json post /api/v2/memories 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/memories: post: tags: - Memories summary: Add Memories description: |- Add memory messages to a project. The `types` field in the request specifies which memory types to add to: - If `types` is empty or not provided, memories are added to all types (episodic and semantic) - If `types` only contains `"episodic"`, memories are added only to Episodic memory - If `types` only contains `"semantic"`, memories are added only to Semantic memory - If `types` contains both, memories are added to both types Each memory message represents a discrete piece of information to be stored in the project's memory system. Messages can include content, metadata, timestamps, and other contextual details. The producer field indicates who created the message, while the produced_for field specifies the intended recipient. These fields help provide context for the memory and if provided should be user-friendly names. The endpoint accepts a batch of messages to be added in a single request. operationId: add_memories requestBody: content: application/json: schema: $ref: '#/components/schemas/AddMemoriesSpec' required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/AddMemoriesResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: AddMemoriesSpec: properties: org_id: type: string title: Org Id description: |2- The unique identifier of the organization. - Must not contain slashes (`/`). - Must contain only letters, numbers, underscores, hyphens, colon, and Unicode characters (e.g., Chinese/Japanese/Korean). No slashes or other symbols are allowed. This value determines the namespace the project belongs to. default: universal examples: - MemVerge - AI_Labs project_id: type: string title: Project Id description: |2- The identifier of the project. - Must be unique within the organization. - Must not contain slashes (`/`). - Must contain only letters, numbers, underscores, hyphens, colon, and Unicode characters (e.g., Chinese/Japanese/Korean). No slashes or other symbols are allowed. This ID is used in API paths and resource locations. default: universal examples: - memmachine - research123 - qa_pipeline types: items: $ref: '#/components/schemas/MemoryType' type: array title: Types description: |2- A list of memory types to include in the search (e.g., episodic, semantic). If empty, all available types are searched. examples: - - episodic - semantic messages: items: $ref: '#/components/schemas/MemoryMessage' type: array minItems: 1 title: Messages description: |2- A list of messages to be added (batch input). Must contain at least one message. type: object required: - messages title: AddMemoriesSpec description: Specification model for adding memories. AddMemoriesResponse: properties: results: items: $ref: '#/components/schemas/AddMemoryResult' type: array title: Results description: The list of results for each added memory message. type: object required: - results title: AddMemoriesResponse description: Response model for adding memories. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError MemoryType: type: string enum: - semantic - episodic title: MemoryType description: Memory type. MemoryMessage: properties: content: type: string title: Content description: The content or text of the message. producer: type: string title: Producer description: |2- The sender of the message. This is a user-friendly name for the LLM to understand the message context. Defaults to 'user'. default: user produced_for: type: string title: Produced For description: |2- The intended recipient of the message. This is a user-friendly name for the LLM to understand the message context. Defaults to an empty string. default: '' timestamp: type: string format: date-time title: Timestamp description: |2- The timestamp when the message was created, in ISO 8601 format. The formats supported are: - ISO 8601 string (e.g., '2023-10-01T12:00:00Z' or '2023-10-01T08:00:00-04:00') - Unix epoch time in seconds (e.g., 1633072800) - Unix epoch time in milliseconds (e.g., 1633072800000) If not provided, the server assigns the current time. If the format is unrecognized, an error is returned. role: type: string title: Role description: |2- The role of the message in a conversation (e.g., 'user', 'assistant', 'system'). Optional; defaults to an empty string. default: '' metadata: additionalProperties: type: string type: object title: Metadata description: |2- Additional metadata associated with the message, represented as key-value pairs. Optional; defaults to an empty object. Retrieval operations may utilize this metadata for filtering. Use 'metadata.{key}' to filter based on specific metadata keys. episode_type: anyOf: - $ref: '#/components/schemas/EpisodeType' - type: 'null' description: |2- The type of an episode (e.g., 'message'). type: object required: - content title: MemoryMessage description: Model representing a memory message. AddMemoryResult: properties: uid: type: string title: Uid description: The unique identifier of the memory message. type: object required: - uid title: AddMemoryResult description: Response model for adding memories. 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 EpisodeType: type: string enum: - message title: EpisodeType description: Episode type. ````