Bitvavo Trading Bot in Python: AI Agent and Algorithmic Trading with LumiBot

This guide shows how to build a Bitvavo trading bot in Python with LumiBot. LumiBot connects to Bitvavo through CCXT, the open source library that talks to more than 100 crypto exchanges. You will create a Bitvavo 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.

Bitvavo at a glance

CCXT exchange id

bitvavo

Markets

Spot

Testnet (sandbox)

No

Credentials

API key, API secret

Live data streams

prices, order book, trades, candles, your orders

CCXT request spacing

about 60 ms between requests

Official site

https://bitvavo.com/

API docs

https://docs.bitvavo.com/

Fees

https://bitvavo.com/en/fees

What is Bitvavo?

Bitvavo is a crypto exchange based in the Netherlands. It offers spot trading with prices in euros.

Sign up for Bitvavo

  1. Create a Bitvavo account and finish identity verification.

  2. Turn on two-factor authentication. Bitvavo will not let you create API keys without it.

  3. Bitvavo has no testnet, so plan to test with a very small amount.

Open a Bitvavo account

Create a Bitvavo API key

  1. Log in on the website (keys cannot be made in the app), click your name and choose Settings.

  2. Open the API tab and click Add new API key.

  3. Enter a name and the IP address of your bot. Separate more than one IP with commas.

  4. Choose the permissions (see below).

  5. Enter your two-factor code and click Confirm. Save the key and secret right away; you cannot see the secret again.

Which permissions to turn on: Turn on View access and Trade digital assets. Bitvavo needs both to read your orders and trades. Leave Withdraw digital assets off: Bitvavo warns that API withdrawals skip two-factor and email checks.

Warning

Never turn on withdrawals for a Bitvavo trading bot key. Bind the key to your server’s IP address when Bitvavo lets you, keep the secret out of your code and out of Git, and delete the key if it ever leaks.

Connect Bitvavo to LumiBot

The simplest way: put these lines in a .env file next to your strategy. LumiBot loads the file, sees TRADING_BROKER=bitvavo and connects to Bitvavo for you, so your strategy needs no broker code.

TRADING_BROKER=bitvavo
BITVAVO_API_KEY=your_apiKey
BITVAVO_API_SECRET=your_secret

LumiBot reads exactly the fields CCXT needs for Bitvavo (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. The keys in the config are CCXT’s own credential names for Bitvavo:

import os

BITVAVO_CONFIG = {
    "exchange_id": "bitvavo",
    "apiKey": os.environ.get("BITVAVO_API_KEY"),
    "secret": os.environ.get("BITVAVO_API_SECRET"),
    "sandbox": False,  # this exchange has no CCXT sandbox
}

from lumibot.brokers import Ccxt

broker = Ccxt(BITVAVO_CONFIG)
# then: MyStrategy(broker=broker, ...)

Either way, LumiBot turns on CCXT’s built-in rate limiting for you.

Testing on Bitvavo

Bitvavo has no sandbox, and CCXT lists no test URL for it, so test with a very small amount. With environment variables, leave BITVAVO_SANDBOX unset. In a code config, always set "sandbox": False: a code config without it turns sandbox mode on, and CCXT then fails because Bitvavo has no test site.

Algorithmic trading example: a simple Bitvavo bot

This bot buys about 50 EUR of bitcoin on Bitvavo once and then holds it. It is a starting point to check that your keys, balances and orders work.

from lumibot.entities import Asset
from lumibot.strategies import Strategy


class BuyBitcoinOnBitvavo(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):
        btc = Asset("BTC", asset_type=Asset.AssetType.CRYPTO)
        if self.get_position(btc) is not None:
            return  # already holding BTC
        price = self.get_last_price(btc, quote=self.quote_asset)
        if price:
            quantity = round(50 / price, 6)  # about 50 EUR worth
            order = self.create_order(btc, 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 = BuyBitcoinOnBitvavo(quote_asset=Asset("EUR", asset_type=Asset.AssetType.CRYPTO))
    strategy.run_live()

Agentic trading example: an AI agent that trades on Bitvavo

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 Bitvavo 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 which coins 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 BitvavoAITrader(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 Bitvavo. You may trade BTC and ETH "
                "against EUR (asset_type 'crypto', quote_symbol 'EUR'), 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/EUR and ETH/EUR prices and your current holdings, "
                "then decide whether to buy, sell or hold."
            ),
            context={"exchange": "Bitvavo", "quote": "EUR", "date": self.get_datetime().isoformat()},
        )


if __name__ == "__main__":
    # LumiBot reads TRADING_BROKER and the keys from your .env file.
    strategy = BitvavoAITrader(quote_asset=Asset("EUR", 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 Bitvavo through CCXT

Market

Listed by CCXT

Spot

Yes

Margin

No

Perpetual swaps

No

Dated futures

No

Options

No

CCXT lists these order features for Bitvavo: market orders, limit orders, stop orders, editing open orders, canceling orders.

Bitvavo tips

  • Bitvavo markets are priced in euros, so use EUR as your quote asset (for example BTC/EUR).

  • Bitvavo supports sub-accounts. An API key can be given access to sub-accounts and internal transfers, but a trading bot does not need those permissions.

Frequently asked questions

Can I build a Bitvavo trading bot in Python?

Yes. Install LumiBot (pip install lumibot), set your Bitvavo keys and use the bitvavo CCXT exchange id as shown above.

Does Bitvavo have a testnet?

CCXT does not list a testnet for Bitvavo. Leave BITVAVO_SANDBOX unset and start with a small amount.

Which API permissions does a Bitvavo bot need?

Turn on View access and Trade digital assets. Bitvavo needs both to read your orders and trades. Leave Withdraw digital assets off: Bitvavo warns that API withdrawals skip two-factor and email checks.

Can an AI agent trade on Bitvavo 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 Bitvavo perpetual futures with LumiBot?

CCXT does not list perpetual swaps for Bitvavo, 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 Bitvavo 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.

Try BotSpot

Sources