ShipsmartAIagentseasier.

Production ready infra for AI. Gateway, Search, RAG and Sandboxing out of the box.

Platform

Everything you need to run agents in production.

Inference

Unified gateway to Claude, GPT, Gemini, Grok, Llama, Mistral and more. One API, every frontier model — with credit-based metering built in.

Sandbox

Isolated execution environments spun up per session. Run untrusted code safely, stream results, and tear down instantly.

RAG

Retrieval-augmented generation on your own data. Chunk, embed, and query documents — grounded answers without hallucination.

Code

Code-first. One SDK, every capability.

src/index.js
import { Agent } from 'easysandbox';
// Initialise the client with your API token
const agent = new Agent(process.env.NOVISURF_API_TOKEN);
// Start a session — sandbox + search tools, streaming enabled
const session = await agent.start({
model: 'novisurf/oversurf-swift-1',
sandbox: true,
tools: ['sandbox', 'search'],
systemPrompt: 'You are a helpful coding assistant.',
});
// Stream the response chunk-by-chunk
const stream = session.stream(
'Write and run a Python script that fetches live BTC price.'
);
for await (const chunk of stream.textStream) {
process.stdout.write(chunk);
}
// Await final result + token usage
const { text, usage } = await stream.done();
console.log(`Cost: $${usage.cost_usd.toFixed(6)}`);
// Tear down the sandbox when done
await session.terminate();
How it works

It is as easy as three steps.

1

Choose your model

Pick from 20+ models across providers like OpenAI, Anthropic, Google, Mistral, and more — all through a single unified API.

2

Ship your agent

Use our SDK to add chat, search, sandboxed code execution, and real-time streaming in minutes, not weeks.

3

Scale without hassle

We handle rate limiting, caching, observability, and failover — so you can focus on building, not infrastructure.

Pricing

Start free. Scale when you need to.

Free

$0

Perfect for getting started and testing our platform.

  • Up to 100 requests/day
  • Access to all base models
  • Basic search capabilities
  • Community support