uAgents is a modular JavaScript framework that empowers developers to build autonomous, decentralized AI agents which can discover peers, exchange messages, collaborate on tasks, and adapt through learning. Agents communicate over libp2p-based gossip protocols, register capabilities via on-chain registries, and negotiate service-level agreements using smart contracts. The core library handles agent lifecycle events, message routing, and extensible behaviors such as reinforcement learning and market-driven task allocation. Through customizable plugins, uAgents can integrate with Fetch.ai’s ledger, external APIs, and oracle networks, enabling agents to perform real-world actions, data acquisition, and decision-making in distributed environments without centralized orchestration.

Swarms.rs is the core Rust runtime for executing swarm-based AI agent programs. It features a modular plugin system to integrate custom logic or AI models, a message-passing layer for peer-to-peer communication, and an asynchronous executor for scheduling agent behaviors. Together, these components allow developers to design, deploy, and scale complex decentralized agent networks for simulation, automation, and multi-agent collaboration tasks.

InAppChat is a comprehensive platform for in-app communication. It features advanced tools such as 1Chatbot and 1Webchat, providing businesses with flexible solutions for peer-to-peer, peer-to-machine, and machine-to-machine chat interactions. By integrating cutting-edge AI and Natural Language Understanding libraries, InAppChat ensures seamless, efficient communication within your applications, enhancing both user engagement and operational support.

DEf-MARL (Decentralized Execution Framework for Multi-Agent Reinforcement Learning) provides a robust infrastructure to execute and train cooperative agents without centralized controllers. It leverages peer-to-peer communication protocols to share policies and observations among agents, enabling coordination through local interactions. The framework integrates seamlessly with common RL toolkits like PyTorch and TensorFlow, offering customizable environment wrappers, distributed rollout collection, and gradient synchronization modules. Users can define agent-specific observation spaces, reward functions, and communication topologies. DEf-MARL supports dynamic agent addition and removal at runtime, fault-tolerant execution by replicating critical state across nodes, and adaptive communication scheduling to balance exploration and exploitation. It accelerates training by parallelizing environment simulations and reducing central bottlenecks, making it suitable for large-scale MARL research and industrial simulations.