polymarket-paper-trader

View on GitHub

Paper trading simulator for Polymarket — built for AI agents. MCP server, live order books, strategy backtesting. Install: npx clawhub install polymarket-paper-trader

★ 39759 forksPythonMITagent-next

MCP server and CLI that gives AI agents $10k paper money to trade real Polymarket order books, with level-by-level fills, slippage and fee modeling, strategy backtesting, P&L stats and a leaderboard. Companion benchmark harness scores LLMs on prediction markets.

Use Cases

Let an AI agent paper-trade Polymarket prediction markets with real order book pricesBacktest trading strategies (momentum, mean reversion, limit grid) on historical snapshotsTrack portfolio P&L, win rate, ROI and max drawdown for agent accountsRun head-to-head strategy battles and multi-account A/B comparisonsBenchmark LLMs on prediction-market decision quality (Brier, calibration, alpha)Publish verifiable leaderboard entries and shareable stats cards from agent trades

Built With

Language: Python
Frameworks: MCP Python SDK · Click · httpx · pytest · setuptools

polymarket-paper-trader

Use Cases

Built With

Tags