agent-next/polymarket-paper-trader

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

What it solves

It provides a risk-free environment for AI agents to trade on Polymarket using "paper money." It solves the problem of testing trading strategies against real-time market data and order books without risking actual capital.

How it works

The project simulates a real exchange by using actual Polymarket order books, meaning trades walk the bid/ask levels and consume liquidity just as they would in a real trade. It implements the exact fee model and slippage tracking used by Polymarket and includes a limit order state machine for GTC (good-til-cancelled) and GTD (good-til-date) orders. It also provides a Model Context Protocol (MCP) server, allowing AI agents to interact with the trading environment through a standardized set of tools for searching markets, executing trades, and managing portfolios.

Who it’s for

Developers building autonomous AI trading agents and researchers testing prediction market strategies.

Highlights

  • Real Exchange Simulation: Uses live order books and exact fee formulas to ensure paper P&L closely matches real-world results.
  • MCP Integration: Full Model Context Protocol support allows agents (like Claude Code) to perform complex trading tasks via tools.
  • Strategy Backtesting: Ability to replay strategies against historical price snapshots.
  • Comprehensive Tooling: Includes a CLI for manual trading, multi-account support for A/B testing, and built-in strategy examples (Momentum, Mean Reversion, and Limit Grid).

Related

  • Project
    caiovicentino/polymarket-mcp-server

    Polymarket MCP Server is a Python‑based MCP server that lets Claude (or any LLM) autonomously discover, analyse, trade, and monitor Polymarket prediction‑market positions. It offers 45 tools across market discovery, analysis, trading, portfolio management, and real‑time monitoring, all guarded by configurable safety limits and full‑node authentication. A web dashboard provides visual control, and the project includes real‑API tests, MIT licensing, and detailed docs for both demo (read‑only) and live‑trading setups.

  • Project
    virattt/ai-hedge-fund

    A proof-of-concept AI-powered hedge fund framework for simulating and backtesting AI-driven trading decisions using financial data and LLMs.

  • Project
    oficcejo/aiagents-stock

    An AI-powered multi-agent stock analysis system that simulates a professional analyst team to provide technical, fundamental, and capital-flow insights for global markets.

  • Project
    TauricResearch/TradingAgents

    TradingAgents is an open‑source, LangGraph‑based framework that orchestrates multiple LLM‑driven agents (fundamentals, sentiment, news, technical, researcher, trader, risk, portfolio) to simulate a full‑stack trading firm. It supports dozens of LLM providers, pulls point‑in‑time market data (SEC EDGAR, FRED, Yahoo Finance, social sentiment), offers checkpointed graph execution, logs decisions for continual learning, and provides a back‑testing CLI to evaluate performance across tickers and dates. Designed for research, not investment advice.

  • Project
    okx/agent-trade-kit

    An AI-powered trading toolkit that connects AI assistants to OKX accounts via the Model Context Protocol, allowing users to trade and manage portfolios using natural language.