@zensation/adapter-sqlite

SQLite storage adapter for ZenBrain memory system. Zero-config, file-based, perfect for development and single-user deployments.

latest

Source

npm

Version: 0.2.3

Version published: 5 days ago

Maintainers: 1

Created: 2 months ago

Source

@zensation/adapter-sqlite

Zero-config SQLite storage adapter for ZenBrain. No database server needed.

Quick Start

npm install @zensation/core @zensation/adapter-sqlite

import { SemanticMemory } from '@zensation/core';
import { SqliteAdapter } from '@zensation/adapter-sqlite';

// File-based (persistent)
const storage = new SqliteAdapter({ filename: './my-memory.db' });

// Or in-memory (testing)
import { createMemoryAdapter } from '@zensation/adapter-sqlite';
const testStorage = createMemoryAdapter();

const memory = new SemanticMemory({ storage });
await memory.storeFact('FSRS outperforms SM-2 by 30%', 'research');

When to Use

Use Case	Adapter
Development / prototyping	SQLite
Single-user desktop app	SQLite
Unit tests	SQLite (`:memory:`)
Multi-user production	PostgreSQL
Vector similarity search	PostgreSQL (pgvector)

Limitations

No vector similarity search (embeddings stored as JSON, not pgvector)
Memory layers fall back to recency-based retrieval instead of semantic search
Single-writer concurrency (WAL mode helps with reads)

Configuration

const storage = new SqliteAdapter({
  filename: './data/memory.db', // default: './zenbrain.db'
  walMode: true,                // default: true (better read concurrency)
  logger: console,              // optional
});

License

Apache 2.0

About ZenBrain

ZenBrain is a seven-layer, neuroscience-derived memory architecture for LLM agents, built as zero-dependency TypeScript and published under Apache-2.0. On LongMemEval-500 three of nine head-to-head answer-quality comparisons hold against Letta, Mem0 and A-Mem — all three against A-Mem, the remaining six are ties, none lost (three competitors x three LLM judges, Bonferroni-corrected, version-matched) — reaching 91.3% of a full-context oracle's binary-judge accuracy at 1/109.6 of the per-query token cost.