API reference · 15 endpoints
Namespaces
Create and manage memory namespaces, their configuration, consolidation, and stats.
- GETList all memory namespaces
- PUTCreate or update memory namespace
- PATCHPartial update memory namespace
- DELETEDelete memory namespace
- POSTAdd/merge memory namespace background (deprecated)
- GETGet namespace configuration
- PATCHUpdate namespace configuration
- DELETEReset namespace configuration
- POSTTrigger consolidation
- POSTRecover failed consolidation
- DELETEClear all observations
- GETGet memory namespace profile
- PUTUpdate memory namespace disposition
- GETGet statistics for memory namespace
- GETMemory ingestion time-series
/v1/default/namespaces/{namespace_id}Create or update memory namespace
Create a new agent or update existing agent with disposition and mission. Auto-fills missing fields with defaults.
Parameters
namespace_idstringpathrequiredRequest body · application/json
namestring | nullDeprecated: display label only, not advertised
dispositionDispositionTraitsDeprecated: use update_namespace_config instead
skepticismintegerrequiredHow skeptical vs trusting (1=trusting, 5=skeptical)
literalismintegerrequiredHow literally to interpret information (1=flexible, 5=literal)
empathyintegerrequiredHow much to consider emotional context (1=detached, 5=empathetic)
disposition_skepticisminteger | nullDeprecated: use update_namespace_config instead
disposition_literalisminteger | nullDeprecated: use update_namespace_config instead
disposition_empathyinteger | nullDeprecated: use update_namespace_config instead
missionstring | nullDeprecated: use update_namespace_config with reflect_mission instead
backgroundstring | nullDeprecated: use update_namespace_config with reflect_mission instead
reflect_missionstring | nullMission/context for Reflect operations. Guides how Reflect interprets and uses memories.
retain_missionstring | nullSteers what gets extracted during retain(). Injected alongside built-in extraction rules.
retain_extraction_modestring | nullFact extraction mode: 'concise' (default), 'verbose', or 'custom'.
retain_custom_instructionsstring | nullCustom extraction prompt. Only active when retain_extraction_mode is 'custom'.
retain_chunk_sizeinteger | nullMaximum token size for each content chunk during retain.
enable_observationsboolean | nullToggle automatic observation consolidation after retain().
observations_missionstring | nullControls what gets synthesised into observations. Replaces built-in consolidation rules entirely.
kind"standard" | "compilation"standard, or compilation to promote memories in from other namespaces
/v1/default/namespaces/{namespace_id}Partial update memory namespace
Partially update an agent's profile. Only provided fields will be updated.
Parameters
namespace_idstringpathrequiredRequest body · application/json
namestring | nullDeprecated: display label only, not advertised
dispositionDispositionTraitsDeprecated: use update_namespace_config instead
skepticismintegerrequiredHow skeptical vs trusting (1=trusting, 5=skeptical)
literalismintegerrequiredHow literally to interpret information (1=flexible, 5=literal)
empathyintegerrequiredHow much to consider emotional context (1=detached, 5=empathetic)
disposition_skepticisminteger | nullDeprecated: use update_namespace_config instead
disposition_literalisminteger | nullDeprecated: use update_namespace_config instead
disposition_empathyinteger | nullDeprecated: use update_namespace_config instead
missionstring | nullDeprecated: use update_namespace_config with reflect_mission instead
backgroundstring | nullDeprecated: use update_namespace_config with reflect_mission instead
reflect_missionstring | nullMission/context for Reflect operations. Guides how Reflect interprets and uses memories.
retain_missionstring | nullSteers what gets extracted during retain(). Injected alongside built-in extraction rules.
retain_extraction_modestring | nullFact extraction mode: 'concise' (default), 'verbose', or 'custom'.
retain_custom_instructionsstring | nullCustom extraction prompt. Only active when retain_extraction_mode is 'custom'.
retain_chunk_sizeinteger | nullMaximum token size for each content chunk during retain.
enable_observationsboolean | nullToggle automatic observation consolidation after retain().
observations_missionstring | nullControls what gets synthesised into observations. Replaces built-in consolidation rules entirely.
kind"standard" | "compilation"standard, or compilation to promote memories in from other namespaces
/v1/default/namespaces/{namespace_id}Delete memory namespace
Delete an entire memory namespace including all memories, entities, documents, and the namespace profile itself. This is a destructive operation that cannot be undone.
Parameters
namespace_idstringpathrequired/v1/default/namespaces/{namespace_id}/backgrounddeprecatedAdd/merge memory namespace background (deprecated)
Deprecated: Use PUT /mission instead. This endpoint now updates the mission field.
Parameters
namespace_idstringpathrequiredRequest body · application/json
contentstringrequiredNew background information to add or merge
update_dispositionbooleandefault trueDeprecated - disposition is no longer auto-inferred from mission
/v1/default/namespaces/{namespace_id}/configGet namespace configuration
Get fully resolved configuration for a namespace including all hierarchical overrides (global → tenant → namespace). The 'config' field contains all resolved config values. The 'overrides' field shows only namespace-specific overrides.
Parameters
namespace_idstringpathrequired/v1/default/namespaces/{namespace_id}/configUpdate namespace configuration
Update configuration overrides for a namespace. Only hierarchical fields can be overridden (LLM settings, retention parameters, etc.). Keys can be provided in Python field format (llm_provider) or environment variable format (ILLUMINA_API_LLM_PROVIDER).
Parameters
namespace_idstringpathrequiredRequest body · application/json
updatesobjectrequiredConfiguration overrides. Keys can be in Python field format (llm_provider) or environment variable format (ILLUMINA_API_LLM_PROVIDER). Only hierarchical fields can be overridden per-namespace.
/v1/default/namespaces/{namespace_id}/configReset namespace configuration
Reset namespace configuration to defaults by removing all namespace-specific overrides. The namespace will then use global and tenant-level configuration only.
Parameters
namespace_idstringpathrequired/v1/default/namespaces/{namespace_id}/consolidateTrigger consolidation
Run memory consolidation to create/update observations from recent memories.
Parameters
namespace_idstringpathrequiredRequest body · application/json
observation_scopesstring[][]Optional list of tag scopes to consolidate. Each scope is a list of tags. Only unconsolidated memories whose tags contain all tags in at least one scope will be processed. If omitted, all unconsolidated memories are processed.
/v1/default/namespaces/{namespace_id}/consolidation/recoverRecover failed consolidation
Reset all memories that were permanently marked as failed during consolidation (after exhausting all LLM retries and adaptive batch splitting) so they are picked up again on the next consolidation run. Does not delete any observations.
Parameters
namespace_idstringpathrequired/v1/default/namespaces/{namespace_id}/observationsClear all observations
Delete all observations for a memory namespace. This is useful for resetting the consolidated knowledge.
Parameters
namespace_idstringpathrequired/v1/default/namespaces/{namespace_id}/profiledeprecatedGet memory namespace profile
Get disposition traits and mission for a memory namespace. Returns 404 if the namespace does not exist.
Parameters
namespace_idstringpathrequired/v1/default/namespaces/{namespace_id}/profiledeprecatedUpdate memory namespace disposition
Update namespace's disposition traits (skepticism, literalism, empathy)
Parameters
namespace_idstringpathrequiredRequest body · application/json
dispositionDispositionTraitsrequiredDisposition traits that influence how memories are formed and interpreted.
skepticismintegerrequiredHow skeptical vs trusting (1=trusting, 5=skeptical)
literalismintegerrequiredHow literally to interpret information (1=flexible, 5=literal)
empathyintegerrequiredHow much to consider emotional context (1=detached, 5=empathetic)
/v1/default/namespaces/{namespace_id}/statsGet statistics for memory namespace
Get statistics about nodes and links for a specific agent
Parameters
namespace_idstringpathrequired/v1/default/namespaces/{namespace_id}/stats/memories-timeseriesMemory ingestion time-series
Memories ingested over a period, bucketed by time and broken down by fact type.
Parameters
namespace_idstringpathrequiredperiodstringquerytime_fieldstringqueryTimestamp column to bucket on. `created_at` (default) = ingest time; `mentioned_at` / `occurred_start` = event time, useful for migrated corpora where ingest time is a single point and doesn't reflect the underlying knowledge timeline. Unknown values fall back to `created_at`.