Quickstart

Get up and running with Reminix in minutes.

Overview

Building with Reminix involves three steps:

1. Build — Create an agent using the runtime
2. Test — Run locally and test with curl
3. Call — Invoke your agent via the API

Already using OpenAI, LangChain, or other AI frameworks?
Check out Python Adapters or TypeScript Adapters to wrap your existing agents instead of building from scratch.

Choose Your Language

What You'll Build

An agent that handles two types of requests:

Test with curl

Once your agent is running locally:

# Health check
curl http://localhost:8080/health

# Invoke
curl -X POST http://localhost:8080/agent/my-agent/invoke \
  -H "Content-Type: application/json" \
  -d '{"input": {"name": "World"}, "stream": false}'

# Chat
curl -X POST http://localhost:8080/agent/my-agent/chat \
  -H "Content-Type: application/json" \
  -d '{"messages": [{"role": "user", "content": "Hello!"}], "stream": false}'

Next Steps

After building and testing locally:

1. Deploy via GitHub — Push to GitHub, auto-deploy
2. Call via API — Invoke from your application

Learn More

• What are Agents? — Understand the basics
• One-off vs Conversational — Choose the right pattern