For agents
@agentskit/memory — for agents
Chat + vector memory backends, plus hierarchical, encrypted, graph, and personalization stores.
Install
npm install @agentskit/memoryPrimary exports
Chat memory (ordered history)
fileChatMemory({ path })— JSON file.sqliteChatMemory— SQLite-backed.redisChatMemory— Redis-backed.
Vector memory
fileVectorMemory({ path })— JSON file.redisVectorMemory— Redis Vector.pgvector,pinecone,qdrant,chroma,upstashVector— BYO-client / HTTP vector adapters. See Vector adapters.
Higher-order memory
createVirtualizedMemory— hot window + cold retriever.createHierarchicalMemory— MemGPT tiers (working / recall / archival).createAutoSummarizingMemory(from@agentskit/core/auto-summarize) — fold oldest into a summary.createEncryptedMemory— AES-GCM over anyChatMemory. See Encrypted memory.createInMemoryGraph— knowledge graph (nodes + edges + BFS). See Graph memory.createInMemoryPersonalization+renderProfileContext— per-subject profile. See Personalization.
Minimal example
import { createInMemoryMemory } from '@agentskit/core'
import { createVirtualizedMemory } from '@agentskit/memory'
const memory = createVirtualizedMemory(createInMemoryMemory(), { maxActive: 50 })Related
- @agentskit/rag — embedders + retrievers on top of vector memory.
- @agentskit/core — the
ChatMemory/VectorMemorycontracts.