API for managing personal memory items with authentication and user-specific data.
API for managing personal memory items with authentication and user-specific data.
This API supports three authentication methods:
X-API-Key headerX-API-Key: <your-api-key>X-Session-Token headerX-Session-Token: <your-session-token>Authorization headerAuthorization: Bearer <token>All endpoints require one of these authentication methods.
Update an existing memory item by ID.
Authentication Required: One of the following authentication methods must be used:
Authorization headerX-API-Key headerX-Session-Token headerRequired Headers:
The API validates content size against MAX_CONTENT_LENGTH environment variable (defaults to 15000 bytes).
Unified policy for graph generation and OMO safety. Use mode='auto' (LLM extraction, constraints applied if provided) or 'manual' (exact nodes). Includes consent, risk, and ACL settings. If schema_id is set, schema's memory_policy is used as defaults.
Unified policy for graph generation and OMO safety. Use mode='auto' (LLM extraction, constraints applied if provided) or 'manual' (exact nodes). Includes consent, risk, and ACL settings. If schema_id is set, schema's memory_policy is used as defaults.
Shorthand DSL for node/edge constraints. Expands to memory_policy.node_constraints and edge_constraints. Formats: - String: 'Task:title' (semantic match on Task.title) - List: ['Task:title', 'Person:email'] (multiple constraints) - Dict: {'Task:title': {'set': {...}}} (with options) Syntax: - Node: 'Type:property', 'Type:prop=value' (exact), 'Type:prop~value' (semantic) - Edge: 'Source->EDGE->Target:property' (arrow syntax) - Via: 'Type.via(EDGE->Target:prop)' (relationship traversal) - Special: '$this', '$previous', '$context:N' Example: 'SecurityBehavior->MITIGATES->TacticDef:name' with {'create': 'never'}
Shorthand DSL for node/edge constraints. Expands to memory_policy.node_constraints and edge_constraints. Formats: - String: 'Task:title' (semantic match on Task.title) - List: ['Task:title', 'Person:email'] (multiple constraints) - Dict: {'Task:title': {'set': {...}}} (with options) Syntax: - Node: 'Type:property', 'Type:prop=value' (exact), 'Type:prop~value' (semantic) - Edge: 'Source->EDGE->Target:property' (arrow syntax) - Via: 'Type.via(EDGE->Target:prop)' (relationship traversal) - Special: '$this', '$previous', '$context:N' Example: 'SecurityBehavior->MITIGATES->TacticDef:name' with {'create': 'never'}
Shorthand DSL for node/edge constraints. Expands to memory_policy.node_constraints and edge_constraints. Formats: - String: 'Task:title' (semantic match on Task.title) - List: ['Task:title', 'Person:email'] (multiple constraints) - Dict: {'Task:title': {'set': {...}}} (with options) Syntax: - Node: 'Type:property', 'Type:prop=value' (exact), 'Type:prop~value' (semantic) - Edge: 'Source->EDGE->Target:property' (arrow syntax) - Via: 'Type.via(EDGE->Target:prop)' (relationship traversal) - Special: '$this', '$previous', '$context:N' Example: 'SecurityBehavior->MITIGATES->TacticDef:name' with {'create': 'never'}
The new content of the memory item
The new content of the memory item
The new content of the memory item
Content type of the memory item
Content type of the memory item
Content type of the memory item
Updated metadata for Neo4J and Pinecone
Updated metadata for Neo4J and Pinecone
Updated context for the memory item
Updated context for the memory item
Updated relationships for Graph DB (neo4J)
Updated relationships for Graph DB (neo4J)
Optional organization ID for multi-tenant memory scoping. When provided, update is scoped to memories within this organization.
Optional organization ID for multi-tenant memory scoping. When provided, update is scoped to memories within this organization.
Optional organization ID for multi-tenant memory scoping. When provided, update is scoped to memories within this organization.
Optional namespace ID for multi-tenant memory scoping. When provided, update is scoped to memories within this namespace.
Optional namespace ID for multi-tenant memory scoping. When provided, update is scoped to memories within this namespace.
Optional namespace ID for multi-tenant memory scoping. When provided, update is scoped to memories within this namespace.
DEPRECATED: Use 'memory_policy' instead. Legacy graph generation configuration. If both memory_policy and graph_generation are provided, memory_policy takes precedence.
DEPRECATED: Use 'memory_policy' instead. Legacy graph generation configuration. If both memory_policy and graph_generation are provided, memory_policy takes precedence.
curl -i -X PUT \
'http://memory.papr.ai/v1/memory/{memory_id}' \
-H 'Content-Type: application/json' \
-H 'X-API-Key: YOUR_API_KEY_HERE' \
-d '{
"content": "Updated meeting notes from the product planning session",
"context": [
{
"content": "Let'\''s update the Q2 product roadmap",
"role": "user"
},
{
"content": "I'\''ll help you update the roadmap. What changes would you like to make?",
"role": "assistant"
}
],
"metadata": {
"emoji tags": "📊,💡,📝,✨",
"emotion tags": "focused, productive, satisfied",
"hierarchical structures": "Business/Planning/Product/Updates",
"topics": "product, planning, updates"
},
"relationships_json": [
{
"metadata": {
"relevance": "high"
},
"related_item_id": "previous_memory_item_id",
"related_item_type": "TextMemoryItem",
"relation_type": "updates"
}
],
"type": "text"
}'Memory successfully updated
List of updated memory items if successful
List of updated memory items if successful
Error message if failed
Error message if failed
Error message if failed
Additional error details or context
Additional error details or context
Additional error details or context
Status message
Status message
Status message
{ "code": 200, "status": "success", "memory_items": [ { … } ], "error": "string", "details": {}, "message": "string", "status_obj": { "pinecone": false, "neo4j": false, "parse": false } }
curl -i -X DELETE \
'http://memory.papr.ai/v1/memory/{memory_id}?skip_parse=false' \
-H 'X-API-Key: YOUR_API_KEY_HERE'{ "code": 200, "status": "success", "message": "string", "error": "string", "memoryId": "", "objectId": "", "deletion_status": { "pinecone": false, "neo4j": false, "parse": false, "qdrant": false }, "details": {} }
If true, return 404 if the memory has consent='none'. Ensures only consented memories are returned.
If true, return 404 if the memory has risk='flagged'. Filters out flagged content.
Maximum risk level allowed. Values: 'none', 'sensitive', 'flagged'. If memory exceeds this, return 404.
Maximum risk level allowed. Values: 'none', 'sensitive', 'flagged'. If memory exceeds this, return 404.
Maximum risk level allowed. Values: 'none', 'sensitive', 'flagged'. If memory exceeds this, return 404.
curl -i -X GET \
'http://memory.papr.ai/v1/memory/{memory_id}?exclude_flagged=false&max_risk=string&require_consent=false' \
-H 'X-API-Key: YOUR_API_KEY_HERE'Memory successfully retrieved
Search results if successful
Search results if successful
Error message if failed
Error message if failed
Error message if failed
Additional error details or context
Additional error details or context
Additional error details or context
Unique identifier for this search query, maps to QueryLog objectId in Parse Server
Unique identifier for this search query, maps to QueryLog objectId in Parse Server
Unique identifier for this search query, maps to QueryLog objectId in Parse Server
{ "code": 200, "data": { "memories": [], "nodes": [] }, "search_id": "abc123def456", "status": "success" }