# react-native-ultrastore v3.1.0: Zero-Dependency MMKV v4 State with On-Device Vector & Stream Cache

> Source: <https://dev.to/samadkhalid_/react-native-ultrastore-v310-zero-dependency-mmkv-v4-state-with-on-device-vector-stream-cache-1lbg>
> Published: 2026-11-16 08:10:04+00:00

Building offline-first AI features in React Native (New Architecture) usually means stitching together MMKV for persistence, Zustand for reactive state, and custom native bridges for vector search or token streaming.

I just shipped **v3.1.0** of **react-native-ultrastore** to unify all three into a single, zero-dependency, synchronous JSI runtime built on MMKV v4 + Nitro Modules.

`useUltraStore`), atomic `setMany` batching, encrypted namespaces, and strict schema migrations with zero async bridge overhead.`react-native-ultrastore/ai`):` Float32Array` buffers without re-validation overhead—ideal for local RAG/embeddings under ~50k vectors.`UltraStreamCache`):` useUltraQuery`, and 42 lifecycle tests.` llms.txt`, `llms-full.txt`, and `.cursorrules` so Cursor and Claude generate accurate, idiomatic code out of the box.

``` js
tsx
import { createUltraStore, useUltraStore } from 'react-native-ultrastore';
import { VectorStore, UltraStreamCache } from 'react-native-ultrastore/ai';

// 1. Synchronous MMKV v4 store
const store = createUltraStore({ id: 'app-store' });

// 2. On-device vector similarity search
const vectors = new VectorStore({ dimensions: 384 });
await vectors.add('doc-1', new Float32Array(384), { title: 'Offline RAG' });
const matches = await vectors.search(queryEmbedding, { topK: 5 });

// 3. Bounded LLM token stream cache
const streamCache = new UltraStreamCache({ maxTokens: 4096 });
streamCache.append('msg-1', 'Hello ');
```


