This open-source project delivers a complete multi-agent reinforcement learning framework built on PyTorch and Unity ML-Agents. It offers decentralized DDPG algorithms, environment wrappers, and training scripts. Users can configure agent policies, critic networks, replay buffers, and parallel training workers. Logging hooks allow TensorBoard monitoring, while modular code supports custom reward functions and environment parameters. The repository includes sample Unity scenes demonstrating collaborative navigation tasks, making it ideal for extending and benchmarking multi-agent scenarios in simulation.

Drive Flow is a flexible framework that empowers developers to design AI-powered workflows by defining sequences of steps. Each step can invoke large language models, execute custom functions, or interact with persistent memory stored in MemoDB. The framework supports complex branching logic, loops, parallel task execution, and dynamic input handling. Built in TypeScript, it uses a declarative DSL to specify flows, enabling clear separation of orchestration logic. Drive Flow also provides built-in error handling, retry strategies, execution context tracking, and extensive logging. Core use cases include AI assistants, automated document processing, customer support automation, and multi-step decision systems. By abstracting orchestration, Drive Flow accelerates development and simplifies maintenance of AI applications.