Build on the AI-Native Cloud

OMNIRIQ hosts autonomous agents with persistent memory (OmniContext), sandboxed execution (OmniRuntime) and self-healing operations (OmniGuard). This page covers everything you need to ship.

1. Quickstart (CLI)

npm install -g omniriq
omniriq login you@example.com yourpassword
omniriq deploy agent.ts

Three commands. No Kubernetes, no Dockerfiles. Your agent gets a public endpoint instantly.

2. Talk to any agent (public endpoint)

curl -X POST "https://omniriq.com/api/run.php?agent=support-bot" \
  -H "Content-Type: application/json" \
  -d '{"message":"How do I reset my password?"}'

Response: {"ok":true,"reply":"...","context_chunks":4,"guard":"ok"} — the agent answers using your indexed OmniContext knowledge plus its conversation memory.

3. JavaScript / Python examples

// JavaScript
const r = await fetch("https://omniriq.com/api/run.php?agent=support-bot", {
  method: "POST", headers: {"Content-Type": "application/json"},
  body: JSON.stringify({ message: "hello" })
}).then(r => r.json());
console.log(r.reply);

# Python
import requests
r = requests.post("https://omniriq.com/api/run.php?agent=support-bot",
                  json={"message": "hello"}).json()
print(r["reply"])

4. Account & fleet management (Console API)

# Deploy with curl (session cookie)
curl -c cj.txt -X POST "https://omniriq.com/api/auth.php?act=login" \
  -H "Content-Type: application/json" -d '{"email":"you@example.com","password":"yourpassword"}'
curl -b cj.txt -X POST "https://omniriq.com/api/agents.php" \
  -H "Content-Type: application/json" \
  -d '{"slug":"sales-sdr","name":"Sales SDR","model":"gpt-4o-mini","system_prompt":"You are an outbound sales agent."}'

5. Framework support

Point LangChain, CrewAI, AutoGen or LlamaIndex at your agent endpoint — any OpenAI-compatible client works. Bring your own model keys or use OMNIRIQ-managed inference.

6. Plans & limits

Questions? support@omniriq.com — ship intelligence, not infrastructure. ⚡