AutoDRIVE Cooperative MARL is an open-source framework designed to train and deploy cooperative multi-agent reinforcement learning (MARL) policies for autonomous driving tasks. It integrates with realistic simulators to model traffic scenarios like intersections, highway platooning, and merging. The framework implements centralized training with decentralized execution, enabling vehicles to learn shared policies that maximize overall traffic efficiency and safety. Users can configure environment parameters, choose from baseline MARL algorithms, visualize training progress, and benchmark agent coordination performance.

This starter project provides a ready-to-use FastAPI application preconfigured for AI agent development. It uses Pydantic for request/response validation, environment-based configuration for OpenAI API keys, and modular endpoint scaffolding. Built-in features include Swagger UI docs, CORS handling, and structured logging, enabling teams to rapidly prototype and deploy AI-driven endpoints without boilerplate overhead. Developers simply define Pydantic models and agent functions to get a production-ready API server.

The AI Agent Terraform Module provides a reusable Terraform configuration that automates the end-to-end provisioning of an AI agent backend. It creates an AWS VPC, IAM roles with least-privilege policies, Lambda functions wired to OpenAI or custom model APIs, API Gateway REST interfaces, and optional Step Functions for workflow orchestration. Users can customize environment variables, scale settings, logging, and monitoring. The module abstracts complex cloud setup into simple inputs, enabling rapid, consistent, and secure deployment of conversational AI agents, task automations, or data processing bots in minutes.

Cooperative Search Environment provides a flexible, gym-compatible multi-agent reinforcement learning environment tailored for cooperative search tasks in both discrete grid and continuous spaces. Agents operate under partial observability and can share information based on customizable communication topologies. The framework supports predefined scenarios like search-and-rescue, dynamic target tracking, and collaborative mapping, with APIs to define custom environments and reward structures. It integrates seamlessly with popular RL libraries such as Stable Baselines3 and Ray RLlib, includes logging utilities for performance analysis, and offers built-in visualization tools for real-time monitoring. Researchers can adjust grid sizes, agent counts, sensor ranges, and reward sharing mechanisms to evaluate coordination strategies and benchmark new algorithms effectively.