NeuralABM is an open-source Python library that leverages PyTorch to integrate neural networks into agent-based modeling. Users can specify agent architectures as neural modules, define environment dynamics, and train agent behaviors using backpropagation across simulation steps. The framework supports custom reward signals, curriculum learning, and synchronous or asynchronous updates, enabling the study of emergent phenomena. With utilities for logging, visualization, and dataset export, researchers and developers can analyze agent performance, debug models, and iterate on simulation designs. NeuralABM simplifies combining reinforcement learning with ABM for applications in social science, economics, robotics, and AI-driven game NPC behaviors. It provides modular components for environment customization, supports multi-agent interactions, and offers hooks for integrating external datasets or APIs for real-world simulations. The open design fosters reproducibility and collaboration through clear experiment configuration and version control integration.

LightJason Benchmark offers a comprehensive set of predefined and customizable scenarios to stress-test and evaluate multi-agent applications built on the LightJason framework. Users can configure agent counts, communication patterns, and environmental parameters to simulate real-world workloads and assess system behavior. Benchmarks gather metrics such as message throughput, agent response times, CPU and memory consumption, logging results to CSV and graphical formats. Its integration with JUnit allows seamless inclusion in automated testing pipelines, enabling regression and performance testing as part of CI/CD workflows. With adjustable settings and extensible scenario templates, the suite helps pinpoint performance bottlenecks, validate scalability claims, and guide architectural optimizations for high-performance, resilient multi-agent systems.