HMAS is an open-source Python framework that enables development of hierarchical multi-agent systems. It offers abstractions for defining agent hierarchies, inter-agent communication protocols, environment integration, and built-in training loops. Researchers and developers can use HMAS to prototype complex multi-agent interactions, train coordinated policies, and evaluate performance in simulated environments. Its modular design makes it easy to extend and customize agents, environments, and training strategies.

MAPF_G2RL is an open-source research framework that bridges graph theory and deep reinforcement learning to tackle the multi-agent path finding (MAPF) problem. It encodes nodes and edges into vector representations, defines spatial and collision-aware reward functions, and supports various RL algorithms such as DQN, PPO, and A2C. The framework automates scenario creation by generating random graphs or importing real-world maps, and orchestrates training loops that optimize policies for multiple agents simultaneously. After learning, agents are evaluated in simulated environments to measure path optimality, makespan, and success rates. Its modular design allows researchers to extend core components, integrate new MARL techniques, and benchmark against classical solvers.

The Foundry AI platform offers a deterministic web simulation and annotation framework, enabling users to collect high-quality labels, benchmark browser agents effectively, and debug performance issues. It ensures reproducible testing and scalable evaluation without the challenges of web drift, IP bans, and rate limits. Built by industry experts, the platform enhances agent evaluation, continuous improvement, and performance debugging in a controlled environment.

Open Agent Leaderboard offers a complete evaluation pipeline for open-source AI agents. It includes a curated task suite covering reasoning, planning, question answering, and tool usage, an automated harness to run agents in isolated environments, and scripts to collect performance metrics such as success rate, runtime, and resource consumption. Results are aggregated and displayed on a web-based leaderboard with filters, charts, and historical comparisons. The framework supports Docker for reproducible setups, integration templates for popular agent architectures, and extensible configurations to add new tasks or metrics easily.

Coval helps companies simulate thousands of scenarios from a few test cases, allowing them to test their voice and chat agents comprehensively. Built by experts in autonomous testing, Coval offers features like customizable voice simulations, built-in metrics for evaluations, and performance tracking. It is designed for developers and businesses looking to deploy reliable AI agents faster.

Dino Reinforcement Learning offers a comprehensive toolkit for training an AI agent to play the Chrome dinosaur game via reinforcement learning. By integrating with a headless Chrome instance through Selenium, it captures real-time game frames and processes them into state representations optimized for deep Q-network inputs. The framework includes modules for replay memory, epsilon-greedy exploration, convolutional neural network models, and training loops with customizable hyperparameters. Users can monitor training progress via console logs and save checkpoints for later evaluation. Post-training, the agent can be deployed to play live games autonomously or benchmarked against different model architectures. The modular design allows easy substitution of RL algorithms, making it a flexible platform for experimentation.