OctagonAI/kalshi-trading-bot-cli

AI-native CLI for trading Kalshi prediction markets. Runs deep fundamental research, generates independent probability estimates, computes edge vs. live order books, and executes trades with Kelly sizing and a 5-gate risk engine.

What it solves

This project provides a command-line interface (CLI) for trading on Kalshi, a prediction market. It solves the difficulty of finding "edge" (profitable opportunities) by combining AI-driven probability estimates with real-time market data, automating the research, risk management, and execution of trades.

How it works

The bot integrates with the Octagon Research API to fetch AI-generated probability estimates for various markets. It calculates the "edge" as the difference between the model's predicted probability and the live order book price. To manage risk, it uses a half-Kelly sizing strategy and a five-gate risk engine to determine how much to invest. Users can search for markets, analyze specific tickers, build diversified baskets of trades using correlation and cluster analysis, and execute buys or sells directly from the terminal.

Who it’s for

It is designed for prediction market traders who want a data-driven, AI-assisted approach to trading on Kalshi, as well as developers who want to programmatically interact with the exchange via a CLI.

Highlights

  • AI-Powered Edge Detection: Uses Octagon Research to find discrepancies between model probabilities and market prices.
  • Advanced Portfolio Management: Includes tools for building diversified baskets with correlation caps and thematic clustering.
  • Risk Engine: Implements Kelly sizing and multiple risk gates (liquidity, correlation, concentration, and drawdown).
  • Learning Loop: Features a reflection system that turns settled positions into lessons and a falsifiable-claim registry for tracking hypotheses.
  • Comprehensive Analysis: Provides Brier scores for calibration, Pearson correlation matrices, and backtesting for baskets and strategies.

Related

  • Project
    oficcejo/alpha-arena-okx

    An AI‑driven Bitcoin futures trading bot for OKX that uses DeepSeek‑chat to generate buy/hold/sell signals, places real stop‑loss/take‑profit orders, and provides a Streamlit web dashboard for live monitoring. Deployable via Baota panel, Docker, or plain Python.

  • Project
    alsk1992/CloddsBot

    Clodds is an open‑source, self‑hosted AI trading terminal. It lets you chat (via Claude or other LLMs) to trade on 10 prediction‑market platforms, 7 futures exchanges, and dozens of Solana/EVM DEXs, launch Solana tokens, mine Bittensor, and run 118+ pre‑built strategies. Install with a single npm command, onboard via a wizard, then use the built‑in WebChat UI or any of 21 messaging apps to place trades, run arbitrage scans, or manage risk. The system includes a unified risk engine, full trade ledger, semantic memory, and a marketplace for AI agents.

  • Project
    hengruiyun/AI-Stock-Master

    AI Stock Master is a Windows/macOS desktop app that blends quantitative stock‑analysis algorithms (RTSI, TMA, MSCI) with a locally‑run LLM (Mini Ollama) to generate natural‑language market reports and trading signals for Chinese, Hong‑Kong and US equities. It’s a research‑oriented tool, not a commercial trading platform.

  • Project
    getkimchi/kimchi

    kimchi is a terminal‑based AI coding assistant that orchestrates multiple LLMs for planning, building, reviewing, exploring, and researching code. It supports multi‑model delegation, persistent Ferment project management, tagging for cost tracking, LSP‑backed language intelligence, and remote session hand‑off.

  • Project
    EthanAlgoX/AIStock

    AI Stock is an agentic research workspace that helps investors analyze stocks, compare investment perspectives, and simulate trading strategies using LLM-powered tools.