agent-memory-persistence
v0.1.0Provide long-term memory persistence for AI agents with SQLite-backed storage, structured metadata, vector embeddings, semantic retrieval, lifecycle management, and queries by user, session, and time.
Installation
Please help me install the skill `agent-memory-persistence` from SkillHub official store.
npx skills add imgolye/agent-memory-persistence
Agent Memory Persistence
Use this skill when an agent needs durable memory storage across sessions.
What it provides
- SQLite-backed persistence for text, metadata, and embedding vectors
- CRUD operations for memory items
- Semantic retrieval with cosine-similarity vector search
- Memory lifecycle operations including expiration cleanup
- Filters by user, session, type, and time window
Project structure
src/MemoryStore.ts: low-level SQLite storage enginesrc/VectorIndex.ts: vector similarity search over stored embeddingssrc/MemoryManager.ts: high-level API used by agentssrc/types.ts: shared TypeScript contracts
Usage pattern
- Create a
MemoryManagerwith a SQLite path. - Write memories with
content, optionalmetadata, and optionalembedding. - Query memories by session/user or use
searchByVector()for semantic lookup. - Periodically call
cleanupExpired()to delete stale memories.
Notes
- Embeddings are stored as JSON arrays in SQLite.
- Vector search is implemented in TypeScript using cosine similarity, which keeps deployment simple and avoids SQLite extensions.
- If memory volume grows substantially, replace
VectorIndexwith an ANN index or SQLite vector extension while preserving theMemoryManagerAPI.