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.

LeanAgent is a Python-based framework designed to streamline the creation of autonomous AI agents. It offers built-in planning modules that leverage large language models for decision making, an extensible tool integration layer for calling external APIs or custom scripts, and a memory management system that retains context across interactions. Developers can configure agent workflows, plug in custom tools, iterate quickly with debugging utilities, and deploy production-ready agents for a variety of domains.

LLM State Machine is an open-source Python framework designed to construct AI agents using explicit state machines. Developers define states as discrete steps—each invoking a large language model or custom logic—and transitions based on outputs. This approach provides clarity, maintainability, and robust error handling for multi-step, LLM-powered workflows, such as document processing, conversational bots, or automation pipelines.

Matcha Agent provides a flexible foundation for building autonomous agents in Python. Developers can configure agents with custom toolsets (APIs, scripts, databases), manage conversational memory, and orchestrate multi-step workflows across different LLMs (OpenAI, local models, etc.). Its plugin-based architecture allows easy extension, debugging, and monitoring of agent behavior. Whether automating research tasks, data analysis, or customer support, Matcha Agent streamlines end-to-end agent development and deployment.

Multi-Agent AI Assistant is a modular Python-based framework that orchestrates multiple GPT-powered agents, each assigned to discrete roles such as planning, research, analysis, and execution. The system supports message passing between agents, memory storage, and integration with external tools and APIs, enabling complex task decomposition and collaborative problem-solving. Developers can customize agent behavior, add new toolkits, and configure workflows via simple configuration files. By leveraging distributed reasoning across specialized agents, the framework accelerates automated research, data analysis, decision support, and task automation. The repository includes sample implementations and templates, allowing rapid prototyping of intelligent assistants and digital workers capable of handling end-to-end workflows in business, education, and research environments.

RL Shooter is a Python-based framework that integrates ViZDoom with OpenAI Gym APIs to create a flexible reinforcement learning environment for FPS games. Users can define custom scenarios, maps, and reward structures to train agents on navigation, target detection, and shooting tasks. With configurable observation frames, action spaces, and logging facilities, it supports popular deep RL libraries such as Stable Baselines and RLlib, enabling clear performance tracking and reproducibility across experiments.

SonAgent is an extensible open-source framework designed for building, organizing, and running AI agents in Python. It provides core modules for memory storage, tool wrappers, planning logic, and asynchronous event handling. Developers can register custom tools, integrate language models, manage long-term agent memory, and orchestrate multiple agents to collaborate on complex tasks. SonAgent’s modular design accelerates the development of conversational bots, workflow automations, and distributed agent systems.

CopilotKit is an open-source Python framework designed for developers to build customized AI agents. It offers a modular architecture where you can register and configure tools — such as file system access, web search, Python REPL, and SQL connectors — then wire them into agents that leverage any supported LLM. Built-in memory modules allow conversation state persistence, while LangGraph lets you define structured reasoning flows for complex tasks. Agents can be deployed in scripts, web services, or CLI apps and scale across cloud providers. CopilotKit works seamlessly with OpenAI, Azure OpenAI, and Anthropic models, empowering automated workflows, chatbots, and data analysis bots.

MACL is a modular Python framework designed to simplify the creation and orchestration of multiple AI agents. It lets you define individual agents with custom skills, set up communication channels, and schedule tasks across an agent network. Agents can exchange messages, negotiate responsibilities, and adapt dynamically based on shared data. With built-in support for popular LLMs and a plugin system for extensibility, MACL enables scalable and maintainable AI workflows across domains like customer service automation, data analysis pipelines, and simulation environments.

Overeasy is a Python-based open-source framework for orchestrating LLM-driven AI agents across various domains. It provides a modular architecture to define agents, configure memory stores, and integrate external tools such as APIs, knowledge bases, and databases. Developers can connect to OpenAI, Azure, or self-hosted LLM endpoints and design dynamic workflows involving single or multiple agents. Overeasy’s orchestration engine handles task delegation, decision making, and fallback strategies, enabling robust digital workers for research, customer support, data analysis, scheduling, and more. Comprehensive documentation and example projects accelerate deployment on Linux, macOS, and Windows.

Agent-Squad is a modular Python framework that empowers teams to design, deploy, and run multi-agent systems for complex task execution. At its core, Agent-Squad lets users configure diverse agent profiles—such as data retrievers, summarizers, coders, and validators—that communicate through defined channels and share memory contexts. By decomposing high-level objectives into subtasks, the framework orchestrates parallel processing and leverages LLMs alongside external APIs, databases, or custom tools. Developers can specify workflows in JSON or code, monitor agent interactions, and adapt strategies dynamically using built-in logging and evaluation utilities. Common applications include automated research assistants, content generation pipelines, intelligent QA bots, and iterative code review processes. The open-source design integrates seamlessly with AWS services, enabling scalable deployments.

Besser Agentic Framework offers a modular toolkit for defining, coordinating, and scaling AI agents. It allows you to configure agent behaviors, integrate external tools and APIs, manage agent memory and state, and monitor execution. Built on Python, it supports extensible plugin interfaces, multi-agent collaboration, and built-in logging. Developers can rapidly prototype and deploy agents for tasks like data extraction, automated research, and conversational assistants, all within a unified framework.

Chainlit is an open-source async Python framework designed to help developers build and deploy scalable Conversational AI and agentic applications rapidly. It supports integrations with popular Python libraries and frameworks to provide a seamless development experience. With Chainlit, users can create production-ready chat applications that can handle complex interactions and retain conversational context.