Memory Tools
get_memories
get_memories
Retrieve a list of user memories with optional filtering.Parameters:
Returns: Memory categories:
| Name | Type | Required | Description |
|---|---|---|---|
categories | array | No | Categories to filter by |
limit | number | No | Maximum number of memories (default: 100) |
offset | number | No | Offset for pagination (default: 0) |
{ "memories": [...] }Example:interesting, core, hobbies, lifestyle, interests, habits, work, skills, learnings, othersearch_memories
search_memories
Semantic search across memories. Returns results ranked by relevance using vector similarity.Parameters:
Returns:
| Name | Type | Required | Description |
|---|---|---|---|
query | string | Yes | Natural language search query |
limit | number | No | Maximum number of results (default: 10) |
{ "memories": [{ ..., "relevance_score": 0.92 }, ...] }Each result includes a relevance_score (0.0 to 1.0) indicating how well it matches the query.Example:create_memory
create_memory
Create a new memory. Category is auto-detected if not provided.Parameters:
Returns:
| Name | Type | Required | Description |
|---|---|---|---|
content | string | Yes | Content of the memory |
category | string | No | Category (auto-detected if omitted) |
{ "success": true, "memory": { ... } }edit_memory
edit_memory
Edit an existing memory’s content.Parameters:
Returns:
| Name | Type | Required | Description |
|---|---|---|---|
memory_id | string | Yes | ID of the memory to edit |
content | string | Yes | New content for the memory |
{ "success": true }delete_memory
delete_memory
Delete a memory by ID.Parameters:
Returns:
| Name | Type | Required | Description |
|---|---|---|---|
memory_id | string | Yes | ID of the memory to delete |
{ "success": true }Conversation Tools
get_conversations
get_conversations
Retrieve a list of conversations with optional date and category filtering.Parameters:
Returns: Conversation categories:
| Name | Type | Required | Description |
|---|---|---|---|
start_date | string | No | Filter after this date (YYYY-MM-DD) |
end_date | string | No | Filter before this date (YYYY-MM-DD) |
categories | array | No | Categories to filter by |
limit | number | No | Maximum number of conversations (default: 20) |
offset | number | No | Offset for pagination (default: 0) |
{ "conversations": [...] } — metadata only. Use get_conversation_by_id for full transcripts.Example:personal, education, health, finance, technology, business, work, social, travel, entertainment, sports, family, and more.search_conversations
search_conversations
Semantic search across conversations. Returns results ranked by relevance using vector similarity.Parameters:
Returns:
| Name | Type | Required | Description |
|---|---|---|---|
query | string | Yes | Natural language search query |
start_date | string | No | Filter after this date (YYYY-MM-DD) |
end_date | string | No | Filter before this date (YYYY-MM-DD) |
limit | number | No | Maximum number of results (default: 10) |
{ "conversations": [...] } — ranked by relevance to the query.Example:get_conversation_by_id
get_conversation_by_id
Retrieve a single conversation by ID, including the full transcript with speaker segments.Parameters:
Returns: Full conversation object with transcript segments, timestamps, structured summary, and metadata.
| Name | Type | Required | Description |
|---|---|---|---|
conversation_id | string | Yes | The ID of the conversation |
Error Handling
All tools return JSON-RPC 2.0 errors when something goes wrong:| Code | Meaning |
|---|---|
-32602 | Invalid parameters (bad date format, unknown category) |
-32001 | Resource not found (memory or conversation doesn’t exist) |
-32002 | Locked content (paid plan required) |
-32601 | Unknown tool name |
Locked Content
Memories and conversations behind the paid plan are handled gracefully:- Memories: Content is truncated to 70 characters with
... - Conversations: Action items and events are hidden from the structured data
- Direct access: Returns error
-32002with a clear message