devin.cursorrules: This project provides a toolkit to supercharge Cursor, Windsurf, or GitHub Copilot with advanced agentic AI capabilities, mimicking Devin's functionality at a fraction of the cost. It enables features like automated planning, extended tool usage, and self-evolution within your existing IDE.; ma-gym: ma-gym provides a collection of multi-agent environments built upon the OpenAI Gym interface, facilitating research and development in multi-agent reinforcement learning. It includes various game-like and task-based environments, as well as wrappers to convert single-agent Gym environments into multi-agent forms for debugging.
Automating data gathering tasks
Research and experimentation in multi-agent reinforcement learning algorithms