The MARL Simulator is designed to facilitate efficient and scalable development of multi-agent reinforcement learning (MARL) algorithms. Leveraging PyTorch's distributed backend, it allows users to run parallel training across multiple GPUs or nodes, significantly reducing experiment runtime. The simulator offers a modular environment interface that supports standard benchmark scenarios—such as cooperative navigation, predator-prey, and grid world—as well as user-defined custom environments. Agents can utilize various communication protocols to coordinate actions, share observations, and synchronize rewards. Configurable reward and observation spaces enable fine-grained control over training dynamics, while built-in logging and visualization tools provide real-time insights into performance metrics.

Autonomys Agents empowers developers to create autonomous AI agents capable of executing complex tasks without manual intervention. Built on Python, the framework provides tools for defining agent behaviors, integrating external APIs and custom functions, and maintaining conversational memory across interactions. Agents can collaborate in multi-agent setups, sharing knowledge and coordinating actions. Observability modules offer real-time logging, performance tracking, and debugging insights. With its modular architecture, teams can extend core components, incorporate new LLMs, and deploy agents across environments. Whether automating customer support, performing data analysis, or orchestrating research workflows, Autonomys Agents streamlines end-to-end development and management of intelligent autonomous systems.

Agent Logging provides a unified logging framework for AI agent frameworks and custom workflows. It intercepts and records each stage of an agent’s execution—prompt generation, tool invocation, LLM response, and final output—along with timestamps and metadata. Logs can be exported in JSON, CSV, or sent to monitoring services. The library supports customizable log levels, hooks for integration with observability platforms, and visualization tools to trace decision paths. With Agent Logging, teams gain insights into agent behavior, spot performance bottlenecks, and maintain transparent records for auditing.