Bring Your Keys
Total privacy. Your AI model API keys never leave the secure enclave. We just provide the compute.

import rooaak
const agent = new rooaak.VM(
{ core: "gpu-h100", model: "llama-3-70b", keys: process.env.AI_KEY }
);
await agent.deploy();Get API KeysWe run them for you. Persistent memory. Auto-sleep. Real-time messaging. Bring your own AI keys and we handle everything else.
Total privacy. Your AI model API keys never leave the secure enclave. We just provide the compute.
No shared pools. Each agent spins up on its own isolated VM instance for maximum throughput.
Deploy 1 or 1,000 agents in seconds. Our orchestrator handles the load-balancing mess for you.
Average time from signup to first agent response. Start building today, not next week.
We monitor it so you do not have to. Your agents stay alive.
Memory persists automatically. Agents remember everything across sessions.
Claude, GPT, Llama, whatever you want. Switch models without rebuilding.
Define personality and point to a context URL. We provision a VM and create your agent.
Real-time SSE connection. Your app sends messages through our SDK, we route to the right agent.
Agent responds using your AI API keys. Full control over models, skills and behavior.
Idle agents auto-sleep to save costs. Wake up instantly on next message. Memory stays intact.
Starter
Free
Starter
$29/mo
Pro
$89/mo
All plans include VM provisioning, state management, auto-sleep, real-time messaging, custom skills, memory and more. You provide your own AI API keys (OpenAI, Anthropic, Gemini, and others).
First agent free. No credit card required.
Get API Keys