Open Source BSD Crypto Trading Bots

Kalshi Trading Bot CLI is an AI-driven command-line tool designed to automate trading strategies on Kalshi prediction markets by combining quantitative modeling with real-time market data. It operates by conducting deep research on events, generating independent probability estimates, and comparing those estimates against current market prices to identify trading opportunities. The system incorporates advanced decision-making logic, including Kelly criterion-based position sizing and a structured multi-step risk evaluation process before executing trades. Built as a CLI application, it allows traders to interact programmatically with markets, making it suitable for automation and integration into larger trading pipelines. The tool emphasizes disciplined trading through its risk engine, ensuring that decisions are filtered through multiple validation layers before capital is committed.

Jesse is an open-source AI agent framework designed to help developers build and orchestrate intelligent workflows that combine large language models (LLMs) with external tools, automation logic, and real-world actions. It acts as an agent manager where you can define tasks, contexts, and tool integrations so that AI reasoning is reliably connected to deterministic procedures like API calls, data retrieval, and task execution. Jesse emphasizes structured outputs, safety boundaries, and explainable reasoning, helping users design agents that don’t just hallucinate responses but can coordinate steps, validate conditions, and interact with systems predictably. It also includes built-in support for evaluation, logging, and orchestration so developers can monitor, test, and improve agent behavior over time. Because it’s framework-agnostic with respect to model providers, Jesse can work with different LLM backends, giving teams flexibility in cost and capability trade-offs.

Catalyst is an algorithmic trading library for crypto-assets written in Python, originally developed to let quants and developers design, backtest, and deploy trading strategies in a unified environment. It builds on top of Zipline, extending that ecosystem to support crypto exchanges and high-resolution historical data (daily and minute bars). Users can express strategies in Python, run backtests against historical price data, and analyze performance through built-in metrics and analytics to evaluate profitability, risk, and behavior under different market conditions. Beyond backtesting, Catalyst was designed to support live trading on multiple crypto exchanges such as Binance, Bitfinex, Bittrex, and Poloniex, bridging simulation and production within the same framework. The library includes a rich set of examples, Docker and conda configurations, and integration points for community resources like forums and Discord for sharing strategies and troubleshooting.

This is a high-frequency trading bot implementation targeting the OKCoin cryptocurrency exchange. The repository states that from 2016 June to January 2017, the strategy turned an initial investment of 6,000 into 250,000. The bot embodies two main strategies: trend following (entering on directional moves) and rebalancing (keeping position exposure near 50%) to mitigate downside in reversals. Position rebalancing around target exposure. Use of OKCoin API client integrations. Trend-following order execution.