:seo_title: p2b Trading Bot in Python: AI Agent and Algorithmic Trading with LumiBot .. Generated by scripts/generate_ccxt_exchange_pages.py from docsrc/_data/. Edit the data, not this page. p2b Trading Bot in Python ========================= .. meta:: :description: Build a p2b trading bot in Python with LumiBot and CCXT. Create p2b API keys, connect them, and run a regular or AI agent strategy. :keywords: p2b trading bot, p2b API, p2b Python, agentic trading p2b, AI trading bot p2b, algorithmic trading p2b, ccxt p2b This guide shows how to build a p2b trading bot in Python with LumiBot, for both AI agent trading and algorithmic trading. LumiBot connects to p2b through CCXT, the open source library that talks to more than 100 crypto exchanges. You will create a p2b 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. p2b at a glance --------------- .. list-table:: :widths: 35 65 * - CCXT exchange id - ``p2b`` * - Markets - Spot * - Testnet (sandbox) - No * - Credentials - API key, API secret * - Live data streams - prices, order book, trades, candles * - CCXT request spacing - about 100 ms between requests * - Official site - https://p2pb2b.com/ * - API docs - https://github.com/P2B-team/p2b-api-docs/blob/master/api-doc.md * - Fees - https://p2pb2b.com/fee-schedule/ What is p2b? ------------ P2B (p2pb2b.com) is a centralized crypto exchange for buying and selling Bitcoin, Ether and a wide range of other tokens. LumiBot uses its spot markets. Sign up for p2b --------------- #. Click Register on p2pb2b.com, enter your email and a password, agree to the Terms of Use and click Sign Up. #. Open the confirmation email from P2B and click the link to verify your email address. #. Turn on two-factor authentication (2FA) in Account, Security (https://p2pb2b.com/account/security). P2B's API docs say to do this before you make an API key. `Open a p2b account `_ Create a p2b API key -------------------- #. Log in to P2B and make sure 2FA is on (Account, Security). #. Open Account, API (https://p2pb2b.com/account/api). #. Generate a new API key and secret. #. Copy the API key and the API secret and keep them somewhere safe. LumiBot needs both. **Which permissions to turn on:** P2B's API docs do not list permission settings for keys. The private API they describe only covers balances and trading (placing, cancelling and checking orders), with no withdrawal endpoint. If the key page offers a withdrawal option, leave it off. A trading bot never needs to move money out. .. warning:: Never turn on withdrawals for a p2b trading bot key. Bind the key to your server's IP address when p2b lets you, keep the secret out of your code and out of Git, and delete the key if it ever leaks. Connect p2b to LumiBot ---------------------- The simplest way: put these lines in a ``.env`` file next to your strategy. LumiBot loads the file, sees ``TRADING_BROKER=p2b`` and connects to p2b for you, so your strategy needs no broker code. .. code-block:: bash TRADING_BROKER=p2b P2B_API_KEY=your_apiKey P2B_API_SECRET=your_secret LumiBot reads exactly the fields CCXT needs for p2b (``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 p2b: .. code-block:: python import os P2B_CONFIG = { "exchange_id": "p2b", "apiKey": os.environ.get("P2B_API_KEY"), "secret": os.environ.get("P2B_API_SECRET"), "sandbox": False, # no sandbox for this exchange } from lumibot.brokers import Ccxt broker = Ccxt(P2B_CONFIG) # then: MyStrategy(broker=broker, ...) Either way, LumiBot turns on CCXT's built-in rate limiting for you. Testing on p2b -------------- P2B has no sandbox, and CCXT lists no test URL for it, so test with a very small amount. With environment variables, leave ``P2B_SANDBOX`` unset. In a code config, set ``"sandbox": False``. Algorithmic trading example: a simple p2b bot --------------------------------------------- This bot buys about 50 USDT of BTC on p2b 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. p2b accepts only limit orders through CCXT, so the example places a limit order just above the last price. .. code-block:: python from lumibot.entities import Asset from lumibot.strategies import Strategy class P2bBuyOnce(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 # This exchange takes only limit orders through CCXT. order = self.create_order(coin, quantity, "buy", limit_price=price * 1.002, quote=self.quote_asset) self.submit_order(order) if __name__ == "__main__": # LumiBot reads TRADING_BROKER and the keys from your .env file. strategy = P2bBuyOnce(quote_asset=Asset("USDT", asset_type=Asset.AssetType.CRYPTO)) strategy.run_live() Agentic trading example: an AI agent that trades on p2b ------------------------------------------------------- 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 p2b 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. .. code-block:: python from lumibot.entities import Asset from lumibot.strategies import Strategy class P2bAITrader(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 p2b. " "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": "p2b", "quote": "USDT", "date": self.get_datetime().isoformat()}, ) if __name__ == "__main__": # LumiBot reads TRADING_BROKER and the keys from your .env file. strategy = P2bAITrader(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 :doc:`AI agents quickstart ` for models, tools and memory. What you can trade on p2b through CCXT -------------------------------------- .. list-table:: :header-rows: 1 :widths: 40 60 * - Market - Listed by CCXT * - Spot - Yes * - Margin - No * - Perpetual swaps - No * - Dated futures - No * - Options - No CCXT lists these order features for p2b: limit orders, editing open orders, canceling orders. p2b tips -------- * P2B's API only creates limit orders (every new order needs a price). Market orders are not supported, so use limit orders in your strategy. * Orders that break a market's limits (minimum amount, step size, tick size or minimum total) are not created. CCXT loads these limits for each market. * P2B allows at most 10 private API requests per second, and it rejects a repeated nonce within the same second. Avoid running two bots on one key at the same time. * BTC trades against USDT, USDC and USD on P2B, for example ``BTC/USDT``. Frequently asked questions -------------------------- **Can I build a p2b trading bot in Python?** Yes. Install LumiBot (``pip install lumibot``), set your p2b keys and use the ``p2b`` CCXT exchange id as shown above. **Does p2b have a testnet?** No testnet is set up for p2b in LumiBot. Start with a small amount, and in a code config set ``"sandbox": False``. **Which API permissions does a p2b bot need?** P2B's API docs do not list permission settings for keys. The private API they describe only covers balances and trading (placing, cancelling and checking orders), with no withdrawal endpoint. If the key page offers a withdrawal option, leave it off. A trading bot never needs to move money out. **Can an AI agent trade on p2b 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 p2b perpetual futures with LumiBot?** CCXT does not list perpetual swaps for p2b, 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 p2b 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 `_ Related guides -------------- * :doc:`CCXT crypto trading with LumiBot ` * :doc:`AI agents quickstart ` * :doc:`Alpaca trading bot ` * :doc:`Bequant trading bot ` * :doc:`Binance US trading bot ` * :doc:`Bit2C trading bot ` Sources ------- * `P2B API documentation (GitHub, official P2B team) `_ (read 2026-10-23) * `P2B blog: How to Register on a Cryptocurrency Exchange? `_ (read 2026-10-23) * `P2B home page `_ (read 2026-10-23) * Exchange id, URLs, markets, credentials and stream support: CCXT 4.5.64 metadata, generated 2026-10-23