Luno Trading Bot in Python¶
This guide shows how to build a Luno trading bot in Python with LumiBot, for both AI agent trading and algorithmic trading. LumiBot connects to Luno through CCXT, the open source library that talks to more than 100 crypto exchanges. You will create a Luno account and API key, connect it, and run two examples: a simple algorithmic trading bot and an agentic trading bot where an AI agent makes the calls.
Luno at a glance¶
CCXT exchange id |
|
Markets |
Spot |
Testnet (sandbox) |
No |
Credentials |
API key, API secret |
Live data streams |
order book, trades |
CCXT request spacing |
about 200 ms between requests |
Official site |
|
API docs |
What is Luno?¶
Luno is a crypto exchange and app where you can buy, sell, store, send and receive Bitcoin and other cryptocurrencies. LumiBot uses it for spot trading against local currencies and stablecoins such as USDT and USDC.
Sign up for Luno¶
Go to www.luno.com and select CREATE ACCOUNT (or use the Luno app), enter your email and a strong password, then confirm your email from the link Luno sends.
Verify your identity: select your initials, then Settings, then Verification, and follow the prompts. You confirm your details and give identity documents or a live selfie.
Keep your sign-in secure. Luno asks you to authorise high-risk actions, such as creating an API key, by push notification or email.
Create a Luno API key¶
Use the Luno website, not the app. Sign in, select your initials in the top left corner to open your profile, then Security.
From the Security menu choose API keys, then select CREATE API KEY.
Name the key and choose its permissions (see below). Tick Restrict IP address and enter your bot’s IP address, then select NEXT.
Copy the API key ID and secret and save them. This is your only chance to see the secret.
Select CREATE API KEY, then approve the push notification or email Luno sends you.
Which permissions to turn on: Pick Custom and turn on only View balance, View transactions, View orders and Create orders. Leave Send to any address and Create withdrawals off. Luno’s help centre says its preset Trading access also lets an app send crypto out of your wallets and withdraw to a bank account, so a custom key is safer for a bot.
Warning
Never turn on withdrawals for a Luno trading bot key. Bind the key to your server’s IP address when Luno lets you, keep the secret out of your code and out of Git, and delete the key if it ever leaks.
Connect Luno to LumiBot¶
The simplest way: put these lines in a .env file next to your strategy. LumiBot loads the file, sees TRADING_BROKER=luno and connects to Luno for you, so your strategy needs no broker code.
TRADING_BROKER=luno
LUNO_API_KEY=your_apiKey
LUNO_API_SECRET=your_secret
LumiBot reads exactly the fields CCXT needs for Luno (apiKey, secret). If one is missing, LumiBot stops at start-up and names the variable you still need.
You can also build the broker in code. This is handy when one script talks to more than one exchange, or when you need extra CCXT options. The keys in the config are CCXT’s own credential names for Luno:
import os
LUNO_CONFIG = {
"exchange_id": "luno",
"apiKey": os.environ.get("LUNO_API_KEY"),
"secret": os.environ.get("LUNO_API_SECRET"),
"sandbox": False, # no sandbox for this exchange
}
from lumibot.brokers import Ccxt
broker = Ccxt(LUNO_CONFIG)
# then: MyStrategy(broker=broker, ...)
Either way, LumiBot turns on CCXT’s built-in rate limiting for you.
Testing on Luno¶
Luno has no sandbox or testnet. Test with a very small amount on your real account, leave LUNO_SANDBOX unset, and in a code config set "sandbox": False.
Algorithmic trading example: a simple Luno bot¶
This bot buys about 50 USDT of BTC on Luno once and then holds it. It is a starting point to check that your keys, balances and orders work. If the exchange’s minimum order is larger, raise the amount.
from lumibot.entities import Asset
from lumibot.strategies import Strategy
class LunoBuyOnce(Strategy):
"""Buy a small amount of BTC once, then hold it."""
def initialize(self):
self.sleeptime = "1H"
self.set_market("24/7") # crypto trades all day, every day
def on_trading_iteration(self):
coin = Asset("BTC", asset_type=Asset.AssetType.CRYPTO)
if self.get_position(coin) is not None:
return # already holding BTC
price = self.get_last_price(coin, quote=self.quote_asset)
if price:
quantity = round(50 / price, 6) # about 50 USDT worth
order = self.create_order(coin, quantity, "buy", quote=self.quote_asset)
self.submit_order(order)
if __name__ == "__main__":
# LumiBot reads TRADING_BROKER and the keys from your .env file.
strategy = LunoBuyOnce(quote_asset=Asset("USDT", asset_type=Asset.AssetType.CRYPTO))
strategy.run_live()
Agentic trading example: an AI agent that trades on Luno¶
Agentic trading means an AI agent reads the market and decides what to do. In this example one LumiBot agent looks at prices and your Luno account, then places the orders itself. There is no Python logic in between: you set the rules in plain English in the prompt, such as what it may trade and how big each order can be. This follows the same pattern as LumiBot’s AI trading team examples.
from lumibot.entities import Asset
from lumibot.strategies import Strategy
class LunoAITrader(Strategy):
"""One AI agent researches the market and places the trades itself."""
def initialize(self):
self.sleeptime = "4H"
self.set_market("24/7")
self.agents.create(
name="trader",
model="openai/gpt-6-luna",
reasoning_effort="high",
allow_trading=True,
system_prompt=(
"You manage a small crypto account on Luno. "
"You may trade BTC and ETH against USDT (asset_type 'crypto', quote_symbol 'USDT'), or hold cash. "
"Before every order, call account_portfolio, account_positions and "
"market_last_price for that exact symbol in the same run. "
"Keep each order under 10% of the account value. "
"Explain each decision in one short paragraph."
),
)
def on_trading_iteration(self):
self.agents["trader"].run(
task_prompt="Review recent BTC/USDT and ETH/USDT prices and your current holdings, then decide whether to buy, sell or hold.",
context={"exchange": "Luno", "quote": "USDT", "date": self.get_datetime().isoformat()},
)
if __name__ == "__main__":
# LumiBot reads TRADING_BROKER and the keys from your .env file.
strategy = LunoAITrader(quote_asset=Asset("USDT", asset_type=Asset.AssetType.CRYPTO))
strategy.run_live()
The agent needs a model key such as OPENAI_API_KEY in your environment. See the AI agents quickstart for models, tools and memory.
What you can trade on Luno through CCXT¶
Market |
Listed by CCXT |
|---|---|
Spot |
Yes |
Margin |
No |
Perpetual swaps |
No |
Dated futures |
No |
Options |
No |
CCXT lists these order features for Luno: market orders, limit orders, editing open orders, canceling orders.
Luno tips¶
Luno’s own API calls Bitcoin
XBT(for example the pairXBTZAR). CCXT maps it toBTC, so in LumiBot writeBTC/USDTorBTC/ZAR.Which pairs you can trade depends on your Luno account, from fiat pairs such as
BTC/GBP,BTC/ZARorBTC/MYRtoBTC/USDTandBTC/USDC. Use a pair your account can trade.You can also set an expiry date on the key. If you do, the bot stops working on that date until you make a new key.
When creating the key, stay on one device (or devices on the same router) and turn off any VPN. Luno says the setup can fail otherwise.
Frequently asked questions¶
Can I build a Luno trading bot in Python?
Yes. Install LumiBot (pip install lumibot), set your Luno keys and use the luno CCXT exchange id as shown above.
Does Luno have a testnet?
No testnet is set up for Luno in LumiBot. Start with a small amount, and in a code config set "sandbox": False.
Which API permissions does a Luno bot need?
Pick Custom and turn on only View balance, View transactions, View orders and Create orders. Leave Send to any address and Create withdrawals off. Luno’s help centre says its preset Trading access also lets an app send crypto out of your wallets and withdraw to a bank account, so a custom key is safer for a bot.
Can an AI agent trade on Luno by itself?
Yes. The agentic example above gives one agent permission to trade. You control what it may trade and how much through its prompt.
Can I trade Luno perpetual futures with LumiBot?
CCXT does not list perpetual swaps for Luno, so use spot markets.
Is LumiBot free?
Yes. LumiBot is open source on GitHub at https://github.com/Lumiwealth/lumibot. You pay only your exchange’s trading fees and, for AI agents, your model provider.
Run it in the cloud with BotSpot¶
Do not want to keep a computer running for your Luno bot? BotSpot is the hosted home for LumiBot strategies and AI trading agents: build with AI, backtest, connect a broker, and watch every trade with logs and alerts.
Sources¶
Luno Help Centre: How do I create a Luno API key? (read 2026-10-23)
Luno API documentation (permissions and currencies) (read 2026-10-23)
Luno Help Centre: How do I sign up for a Luno account? (read 2026-10-23)
Luno Help Centre: How do I verify my identity with Luno? (read 2026-10-23)
Luno Help Centre: What is authorisation and how does it work? (read 2026-10-23)
Exchange id, URLs, markets, credentials and stream support: CCXT 4.5.64 metadata, generated 2026-10-23