Skip to content
Flow Like logo Flow Like Docs

Compress Memory Node

AI/Memory

Compress Memory

Compresses old memory observations into a summary using an LLM, then replaces them in the store. Runs the embedding model to store the summary vector.

memory_compressllmLong running
Inputs4
Outputs4
Security exposure3/10
Packagellm

Ratings

Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.

SecurityAttack surface and exposure impact.
3/10High
PrivacyPotential sensitivity of processed data.
5/10Medium
PerformanceRuntime or resource pressure.
5/10Medium
GovernancePolicy, audit, or compliance impact.
4/10Medium
ReliabilityOperational stability considerations.
3/10High
CostExternal or compute cost impact.
7/10Low

Input Pins

4

Input

Execution
exec_in

Trigger

Memory Config

Struct
memory_config

MemoryConfig from Create Memory Config node

MemoryConfigMemoryConfig7 fields
databaseNodeDBConnectionrequired
cache_keystringrequired
embedding_modelCachedEmbeddingModelrequired
cache_keystringrequired
model_typeBitTypesrequired
enum "Llm", "Vlm", "Tts", "Stt"...
max_context_tokensinteger:uint32required
format uint32min 0
recall_strategyRecallStrategyrequired
enum "RecentFirst", "Relevance", "Hybrid"
recall_top_kinteger:uint32required
format uint32min 0
auto_compressbooleanrequired
compress_thresholdinteger:uint32required
format uint32min 0
Schema enforced

Observations

Struct Array
observations

Array of memory records to compress (typically older observations from Search Memory)

Compression Model

Struct
model

LLM model Bit for generating the summary

BitBit19 fields
idstring
default ""
typeBitTypes
enum "Llm", "Vlm", "Tts", "Stt"...default "Other"
metaMap<string, Metadata>
default {}
*Metadatamap value
namestringrequired
descriptionstringrequired
long_descriptionstring | null
release_notesstring | null
tagsArray<string>required
itemsstringarray item
+11 more fields
authorsArray<string>
default []
itemsstringarray item
repositorystring | null
default null
download_linkstring | null
default null
file_namestring | null
default null
hashstring
default ""
sizeinteger | null
format uint64default nullmin 0
hubstring
default ""
parametersvalue
default null
versionstring | null
default null
licensestring | null
default null
dependenciesArray<string>
default []
itemsstringarray item
dependency_tree_hashstring
default ""
createdstring
default ""
updatedstring
default ""
model_slugstring | null
default null
+1 more fields
Schema enforced

Output Pins

4

Done

Execution
exec_out

Fires when compression completes

Summary

String
summary_text

The compressed summary text

Compressed Count

Integer
compressed_count

Number of observations that were compressed

Stats

Struct
stats

Token usage and model statistics from the compaction LLM call

LLMUsageStatsLLMUsageStats5 fields
usageUsagerequired
completion_tokensinteger:uint32required
format uint32min 0
prompt_tokensinteger:uint32required
format uint32min 0
total_tokensinteger:uint32required
format uint32min 0
costnumber | null
format double
prompt_tokens_detailsanyOf (2)
variant 1PromptTokenDetailsvariant
cached_tokensinteger | null
format uint32min 0
audio_tokensinteger | null
format uint32min 0
variant 2nullvariant
+2 more fields
modelstring | null
duration_msinteger | null
format uint64min 0
iterationsinteger | null
format uint32min 0
callsArray<ModelCallEntry>
itemsModelCallEntryarray item
modelstringrequired
usageUsagerequired
completion_tokensinteger:uint32required
format uint32min 0
prompt_tokensinteger:uint32required
format uint32min 0
total_tokensinteger:uint32required
format uint32min 0
costnumber | null
format double
prompt_tokens_detailsanyOf (2)
+2 more fields
duration_msinteger | null
format uint64min 0
Schema enforced

Node Info

Internal name
memory_compress
Category
AI/Memory
Version
1