Start Building

Choose your path. Both lead to a deployed worker earning ALLO.

🪄

Vibe Build

AI assisted, beginner friendly

✦Pick a ready to use prompt for your topic
✦Paste into Claude, ChatGPT, or Cursor
✦Deploy your first worker in under an hour
✦No ML experience required

✓ Selected

🔧

Manual Build

Full architecture, for devs

✦Step by step architecture walkthrough
✦Real code: Flask API, Go adapter, Docker
✦Full control over your prediction logic
✦Copy paste config and deploy commands

Tap to explore

Build with AI

You don't need an ML degree. Pick a topic, copy the prompt into your favorite AI coding assistant, and deploy your first worker in under an hour.

📋

1. Pick a Prompt

Choose a topic and difficulty that matches your comfort level

🤖

2. Paste into AI

Claude, ChatGPT, Cursor, Copilot... any AI coding assistant works

🚀

3. Deploy & Earn

Wrap it in Docker, push to Forge, and start earning ALLO

🎯 ETH/USD 10 minute prediction📊 Beginner⏱️ ~30 minutes

paste this into your AI assistant

I want to build an Allora worker that predicts ETH/USD price 10 minutes into the future.

Here's what I need:
1. A Python Flask API with a /inference/<token> endpoint
2. Use a simple approach: fetch recent ETH prices from CoinGecko's free API, calculate a weighted moving average of the last 20 candles, and add momentum adjustment based on the last 5 candles
3. Return the prediction as JSON: {"value": "predicted_price"}
4. The server should run on port 8000

Keep it simple. No complex ML libraries needed. Just requests, flask, and numpy.
Include error handling so it returns the last known price if the API call fails.

💡 Tip: After the AI generates your code, ask it to also write a Dockerfile and requirements.txt

🔮 What happens after you paste this prompt?

1.Your AI assistant writes the complete main.py with prediction logic

2.Ask it to add a Dockerfile and requirements.txt

3.Clone the Allora starter kit and drop your files in

4.Configure your topic in config.json and run docker compose up

"At Numerai's DeAI Day in Vienna, a participant deployed their first Allora worker in under an hour using an AI coding agent."

You don't need to be an ML engineer. You need a good idea and an AI assistant.

🔨

Allora Forge: The Fast Track

Don't want to deploy straight to mainnet? Start with Forge, Allora's competition platform where you build, test, and prove your models first.

How It Works

1️⃣Setup & Register

Create a worker node, fund it via testnet faucet, and register to a competition topic.

2️⃣Compete & Earn Hammers

Submit log-return predictions for BTC, ETH, SOL, NEAR across 1hr, 8hr, 1d, 7d timeframes. Accuracy = Hammers.

3️⃣Top 32 → Mainnet

Top 32 performers per topic earn a mainnet deployment slot. Real ALLO rewards await.

Mainnet Qualification Bar

Your model needs to hit these statistical thresholds across rolling windows:

Directional Accuracy> 55%

DA 95% CI Lower Bound> 52%

Pearson Correlation> 0.05

WRMSE Improvement> 10%

WZPTAE Improvement> 20%

💡 A simple moving average model can qualify for mainnet. You don't need a complex model to start earning ALLO.

Enter the Forge ↗Read the Research ↗

Recommended Data Sources for Your Model

Price Data

Tiingo, CoinGecko, CoinMarketCap

On-Chain

Etherscan, Dune, Space and Time

Trading Data

Binance API, Coinbase API

Features

OHLCV, gas fees, sentiment, order book

Now let's talk about earning...

How to Earn ALLO →