Shepherding is an open-source simulation framework designed for reinforcement learning researchers and developers to study and implement multi-agent herding tasks. It provides a Gym-compatible environment where agents can be trained to perform behaviors such as flanking, collecting, and dispersing target groups across continuous or discrete spaces. The framework includes modular reward shaping functions, environment parameterization, and logging utilities for monitoring training performance. Users can define obstacles, dynamic agent populations, and custom policies using TensorFlow or PyTorch. Visualization scripts generate trajectory plots and video recordings of agent interactions. Shepherding’s modular design allows seamless integration with existing RL libraries, enabling reproducible experiments, benchmarking of novel coordination strategies, and rapid prototyping of AI-driven herding solutions.

Aeiva is a developer-first platform that enables you to create, deploy, and evaluate autonomous AI agents within flexible simulation environments. It features a plugin-based engine for environment definition, intuitive APIs to customize agent decision loops, and built-in metrics collection for performance analysis. The framework supports integration with OpenAI Gym, PyTorch, and TensorFlow, plus real-time web UI for monitoring live simulations. Aeiva’s benchmarking tools let you organize agent tournaments, record results, and visualize agent behaviors to fine-tune strategies and accelerate multi-agent AI research.