Memory Agent Nodes

Query the long-term memory database (RAG) and unpack the returned memory documents.

3 nodes.

Node	Registry path
Query Context DB	agents/memory/QueryContextDB
Referenced Characters	agents/memory/ReferencedCharacters
Unpack Memory Document	agents/memory/UnpackMemoryDocument

Query Context DB

agents/memory/QueryContextDB

Queries the memory agent's context database with one or more queries and collects the matching documents, up to a total token budget.

Inputs

Input	Type	Description
state	any	The graph state
queries	list,str	(optional) The queries to run (list, or a single query string)
meta_filters	dict	Metadata filters to constrain the results (optional)
max_tokens	int	The maximum total tokens of results to return (optional)
fn_filter	function	Function that receives a result and returns whether to keep it (optional)
fn_formatter	function	Function that receives a result and returns its formatted replacement (optional)
viewer	str,character	Return only what this character knows (optional). With Character Perspectives on, results come from the character's own memories; otherwise entries the character does not know are left out.

Outputs

Output	Type	Description
state	any	The state input, passed through
results	list	The list of matching documents

Properties

Property	Type	Default	Description
queries	list	[]	The queries to use to query the context database
meta_filters	dict	{}	The meta filters to apply to the results
max_tokens	int	1024	The maximum number of tokens to return
limit	int	10	The number of N best results to consider per query
iterate	int	3	The number of results to return per query

Referenced Characters

agents/memory/ReferencedCharacters

Which characters a text refers to, by name, by a mapped alias or, with the decision model, by pronoun, title or nickname ("her brother", "the Captain"). The candidates default to the characters not in the scene.

Uses the memory agent's entity lookup setting "Use Decision Model" and the same editable decision policy; without a decision model, or when it is uncertain, names and aliases are matched in the text.

Inputs

Input	Type	Description
state	any	graph state (passthrough)
text	str	the text to check
candidates	list	character names to check (optional)

Outputs

Output	Type	Description
state	any	graph state
characters	list	the candidates the text refers to, in candidate order

Unpack Memory Document

agents/memory/UnpackMemoryDocument

Unpacks a memory document into its individual fields.

Inputs

Input	Type	Description
document	memory/document	The memory document to unpack

Outputs

Output	Type	Description
document	memory/document	The memory document, passed through
meta	dict	The document's metadata dict
id	str	The document's ID in the memory database
raw	dict	The document's raw content
as_text	str	The document rendered as text
as_dict	dict	The document as a dict
context_id	context_id	The document's context ID