SDKs

AINative provides client SDKs for popular frameworks. Each SDK wraps the REST API with framework-native patterns.

Available SDKs

SDK	Package	Install	Framework
React	@ainative/react-sdk	npm i @ainative/react-sdk	React 18+
Next.js	@ainative/nextjs-sdk	npm i @ainative/nextjs-sdk	Next.js 13+ (App Router + Pages)
Svelte	@ainative/svelte-sdk	npm i @ainative/svelte-sdk	Svelte/SvelteKit
Vue	@ainative/vue-sdk	npm i @ainative/vue-sdk	Vue 3
Python (LangChain)	langchain-zerodb	pip install langchain-zerodb	LangChain
Python (LlamaIndex)	llama-index-vector-stores-zerodb	pip install llama-index-vector-stores-zerodb	LlamaIndex
Python (Direct)	zerodb-mcp	pip install zerodb-mcp	Any Python
CLI	zerodb-cli	npx zerodb-cli init	Terminal

React SDK

import { AINativeProvider, useChat, useCredits } from '@ainative/react-sdk';

function App() {
  return (
    <AINativeProvider apiKey="your-key" projectId="your-project">
      <Chat />
    </AINativeProvider>
  );
}

function Chat() {
  const { messages, sendMessage, isLoading } = useChat();
  const { balance } = useCredits();

  return (
    <div>
      <p>Credits: {balance}</p>
      {messages.map(m => <p key={m.id}>{m.content}</p>)}
      <button onClick={() => sendMessage("Hello")}>Send</button>
    </div>
  );
}

Next.js SDK

// app/api/chat/route.ts (App Router)
import { createServerClient } from '@ainative/nextjs-sdk';

export async function POST(req: Request) {
  const client = createServerClient();
  const { messages } = await req.json();

  const stream = await client.chat.completions.create({
    model: 'meta-llama/llama-3.3-70b-instruct',
    messages,
    stream: true,
  });

  return new Response(stream);
}

Python — LangChain

from langchain_zerodb import ZeroDBVectorStore

store = ZeroDBVectorStore(
    api_key="your-api-key",
    project_id="your-project-id",
)

# Add documents (embeddings free)
store.add_texts(["Your content here"])

# Search
results = store.similarity_search("your query", k=5)

Python — LlamaIndex

from llama_index_zerodb import ZeroDBVectorStore
from llama_index.core import VectorStoreIndex

store = ZeroDBVectorStore(api_key="key", project_id="id")
index = VectorStoreIndex.from_vector_store(store)
engine = index.as_query_engine()
response = engine.query("What is ZeroDB?")

Next Steps

• Quick Start — Get up and running
• API Reference — REST API docs
• MCP Setup — Agent tool integration