Introduction
MCP Tools
REST API
- GETGet Config
- PUTUpdate Memory Config Endpoint
- GETGet Episodic Memory Config
- PUTUpdate Episodic Memory Config
- GETGet Long Term Memory Config
- PUTUpdate Long Term Memory Config
- GETGet Short Term Memory Config
- PUTUpdate Short Term Memory Config
- GETGet Semantic Memory Config
- PUTUpdate Semantic Memory Config
- GETGet Resources
Typescript REST SDK
PythonSDK Client
curl --request PUT \
--url http://localhost:8080/api/v2/config/memory \
--header 'Content-Type: application/json' \
--data '
{
"episodic_memory": {
"long_term_memory": {
"embedder": "<string>",
"reranker": "<string>",
"vector_graph_store": "<string>"
},
"short_term_memory": {
"llm_model": "<string>",
"message_capacity": 1
},
"long_term_memory_enabled": true,
"short_term_memory_enabled": true,
"enabled": true
},
"semantic_memory": {
"enabled": true,
"database": "<string>",
"llm_model": "<string>",
"embedding_model": "<string>",
"ingestion_trigger_messages": 1,
"ingestion_trigger_age_seconds": 1
}
}
'{
"success": true,
"message": "<string>"
}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:
- Add a new resource via
POST /config/resources/embeddersorPOST /config/resources/language_models - Call this endpoint to point the memory configuration at the new resource
- The configuration is persisted to the configuration file
Example - update episodic long-term memory to use a new embedder:
{
"episodic_memory": {
"long_term_memory": {
"embedder": "my-new-embedder"
}
}
}
Example - update semantic memory to use a new LLM and embedder:
{
"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).
curl --request PUT \
--url http://localhost:8080/api/v2/config/memory \
--header 'Content-Type: application/json' \
--data '
{
"episodic_memory": {
"long_term_memory": {
"embedder": "<string>",
"reranker": "<string>",
"vector_graph_store": "<string>"
},
"short_term_memory": {
"llm_model": "<string>",
"message_capacity": 1
},
"long_term_memory_enabled": true,
"short_term_memory_enabled": true,
"enabled": true
},
"semantic_memory": {
"enabled": true,
"database": "<string>",
"llm_model": "<string>",
"embedding_model": "<string>",
"ingestion_trigger_messages": 1,
"ingestion_trigger_age_seconds": 1
}
}
'{
"success": true,
"message": "<string>"
}Body
Specification for updating memory configuration.
Partial update for episodic memory configuration. Only supplied
fields are updated; omitted fields remain unchanged.
Show child attributes
Show child attributes
Partial update for semantic memory configuration. Only supplied
fields are updated; omitted fields remain unchanged.
Show child attributes
Show child attributes