> ## 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. # Create Project > Create a new project. This endpoint creates a project under the specified organization using the provided identifiers and configuration. Both `org_id` and `project_id` follow the rules: no slashes; only letters, numbers, underscores, hyphens, colon, and Unicode characters. Each project acts as an isolated memory namespace. All memories (episodes) inserted into a project belong exclusively to that project. Queries, listings, and any background operations such as memory summarization or knowledge extraction only access data within the same project. No cross-project memory access is allowed. If a project with the same ID already exists within the organization, the request will fail with an error. Returns the fully resolved project record, including configuration defaults applied by the system. ## OpenAPI ````yaml /openapi.json post /api/v2/projects 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/projects: post: tags: - Projects summary: Create Project description: |- Create a new project. This endpoint creates a project under the specified organization using the provided identifiers and configuration. Both `org_id` and `project_id` follow the rules: no slashes; only letters, numbers, underscores, hyphens, colon, and Unicode characters. Each project acts as an isolated memory namespace. All memories (episodes) inserted into a project belong exclusively to that project. Queries, listings, and any background operations such as memory summarization or knowledge extraction only access data within the same project. No cross-project memory access is allowed. If a project with the same ID already exists within the organization, the request will fail with an error. Returns the fully resolved project record, including configuration defaults applied by the system. operationId: create_project requestBody: content: application/json: schema: $ref: '#/components/schemas/CreateProjectSpec' example: org_id: acme-corp project_id: agent-smith-v1 description: Primary memory store for customer support agent config: embedder: openai-text-3-small reranker: cohere-rerank-english-v3.0 required: true responses: '201': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ProjectResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: CreateProjectSpec: 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. 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. examples: - memmachine - research123 - qa_pipeline description: type: string title: Description description: |2- A human-readable description of the project. Used for display purposes in UIs and dashboards. Optional; defaults to an empty string. default: '' examples: - Test project for RAG pipeline - Production semantic search index config: $ref: '#/components/schemas/ProjectConfig' description: |2- Configuration settings associated with this project. Defines which models (reranker, embedder) to use. If any values within `ProjectConfig` are empty, global defaults are applied. type: object required: - org_id - project_id title: CreateProjectSpec description: |- Specification model for creating a new project. A project belongs to an organization and has its own identifiers, description, and configuration. The project ID must be unique within the organization. ProjectResponse: properties: org_id: type: string title: Org Id description: |2- The unique identifier of the organization this project belongs to. Returned exactly as stored by the system. project_id: type: string title: Project Id description: |2- The identifier of the project. This value uniquely identifies the project within the organization. description: type: string title: Description description: |2- A human-readable description of the project. Used for display purposes in UIs and dashboards. Optional; defaults to an empty string. default: '' config: $ref: '#/components/schemas/ProjectConfig' description: |2- Configuration settings associated with this project. Defines which models (reranker, embedder) to use. If any values within `ProjectConfig` are empty, global defaults are applied. type: object required: - org_id - project_id title: ProjectResponse description: >- Response model returned after project operations (e.g., creation, update, fetch). Contains the resolved identifiers and configuration of the project as stored in the system. Field formats follow the same validation rules as in `CreateProjectSpec`. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ProjectConfig: properties: backend: anyOf: - type: string enum: - declarative - event - type: 'null' title: Backend description: Long-term memory backend. New projects should set 'event'. reranker: type: string title: Reranker description: |2- The name of the reranker model to use for this project. - Must refer to a reranker model defined in the system configuration. - If set to an empty string (default), the globally configured reranker will be used. Rerankers typically re-score retrieved documents to improve result quality. default: '' examples: - bge-reranker-large - my-custom-reranker embedder: type: string title: Embedder description: |2- The name of the embedder model to use for this project. - Must refer to an embedder model defined in the system configuration. - If set to an empty string (default), the globally configured embedder will be used. Embedders generate vector embeddings for text to support semantic search and similarity operations. default: '' examples: - bge-base-en - my-embedder vector_graph_store: type: string title: Vector Graph Store description: VectorGraphStore resource id (declarative backend only) default: '' vector_store: type: string title: Vector Store description: VectorStore resource id (event backend only) default: '' segment_store: type: string title: Segment Store description: >- SQL engine resource id backing the segment store (event backend only) default: '' properties_schema: additionalProperties: type: string type: object title: Properties Schema description: >- User-defined filterable properties (event backend only). Maps name to type ("bool", "int", "float", "str", "datetime"). type: object title: ProjectConfig description: >- Project configuration model. Identifies the long-term-memory backend and the resource ids it should bind to. If any string field is left empty (""), the server falls back to its globally-configured defaults. Backend selection: - `backend="event"` (default for new projects): uses VectorStore + SegmentStore. Requires `vector_store` and `segment_store`. - `backend="declarative"`: uses VectorGraphStore. Requires `vector_graph_store`. - Empty/null `backend`: server falls back to its parse-time default (declarative, for backwards compatibility with pre-discriminator clients). 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 ````