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.

Enso is a browser-based platform that lets users create custom AI agents through a visual flow-based builder. Users drag and drop modular code and AI components, configure API integrations, embed chat interfaces, and preview interactive workflows in real time. Once designed, agents can be tested instantly and deployed with one click to the cloud or exported as containers. Enso simplifies complex automation tasks by combining no-code simplicity with full code extensibility, enabling rapid development of intelligent assistants and data-driven workflows.

CommNet is a research-oriented library that implements the CommNet architecture, allowing multiple agents to share hidden states at each timestep and learn to coordinate actions in cooperative environments. It includes PyTorch model definitions, training and evaluation scripts, environment wrappers for OpenAI Gym, and utilities for customizing communication channels, agent counts, and network depths. Researchers and developers can use CommNet to prototype and benchmark inter-agent communication strategies on navigation, pursuit–evasion, and resource-collection tasks.

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.

ePH-MAPF provides an efficient pipeline for computing collision-free paths for dozens to hundreds of agents on grid-based maps. It uses prioritized heuristics, incremental search techniques, and customizable cost metrics (Manhattan, Euclidean) to balance speed and solution quality. Users can select between different heuristic functions, integrate the library into Python-based robotics systems, and benchmark performance on standard MAPF scenarios. The codebase is modular and well-documented, enabling researchers and developers to extend it for dynamic obstacles or specialized environments.