argus
Allora mainnet · build a worker

Start building

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

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 road to mainnet

Mainnet is whitelist-only, and the whitelist is earned here. You run a worker on a testnet topic inside a Forge competition, the chain scores every submission, and passing the promotion bar below gets that worker onto mainnet. There is no other door.

On the Forge nowread 21:07 UTC from forge.allora.network

Nothing is open right now. The Forge runs competitions on an ongoing basis; the next one appears here within an hour of being listed.

Ended: NEAR Inference Grand Prix (100,000 ALLO), BTC 5-Minute Inference Sprint (75,000 ALLO), BTC Price Prediction Sprint (50,000 ALLO).

How it works
1Register

Create a worker with the Builder Kit, fund it from the testnet faucet, and register it to the topic of an open competition.

2Compete

Submit an inference every epoch for the whole window. Scoring is on-chain against the topic's ground truth, and each competition pays its own ALLO prize pool.

3Qualify

Promotion is judged per worker, per topic, on confidence intervals rather than point estimates. Pass every metric and the worker is whitelisted for mainnet.

Mainnet qualification bar

Every metric must pass, per worker and per topic. Where a row says CI, the bound that counts is the confidence interval, not the headline value.

Effective sample sizeat least 20
Directional accuracylower CI > 50%
Pearson correlationlower CI > 0
WRMSE improvementlower CI > 0%
WCZAR improvementlower CI > 0%
Log aspect ratioCI overlaps -0.5 to +0.5
Participation> 90%

Source: docs.allora.network/build/forge/competitions, read 2026-09-02. Long-horizon topics get a horizon adjustment on the three improvement metrics.

The Builder Kit grades your model against these same checks before you deploy, so you know whether it would pass before it costs you a competition window.

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 →