ANAC-agents is a Python-based framework that centralizes multiple negotiation agent implementations for the Automated Negotiating Agents Competition (ANAC). Each agent within the repository embodies distinct strategies for utility modeling, proposal generation, concession tactics, and acceptance criteria, facilitating comparative studies and rapid prototyping. Users can define negotiation domains with custom issues and preference profiles, then simulate bilateral negotiations or tournament-style competitions across agents. The toolkit includes configuration scripts, evaluation metrics, and logging utilities to analyze negotiation dynamics. Researchers and developers can extend existing agents, test novel algorithms, or integrate external learning modules, accelerating innovation in automated bargaining and strategic decision-making under incomplete information.

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.

ChatGPT OpenAI Smart Speaker is a developer framework for building your own voice-activated AI assistant. It runs on devices like Raspberry Pi, Linux PCs, macOS, or Windows machines. Using standard Python libraries for speech recognition and text-to-speech synthesis, it listens for a wake word, captures your question, forwards it to the OpenAI ChatGPT API, and reads back responses in real time. You can extend it with custom commands, integrate smart home controls, or use it for educational voice AI demos.

Cyrano is an open-source Python framework and CLI for creating AI agents that orchestrate large language models and external tools through natural language prompts. Users can define custom tools (functions), configure memory and token limits, and handle callbacks. Cyrano handles parsing JSON responses from LLMs and executes specified tools in sequence. It emphasizes simplicity, modularity, and zero external dependencies, enabling developers to prototype chatbots, build automated workflows, and integrate AI capabilities into applications quickly.

Fast Reinforcement Learning is a specialized Python framework designed to accelerate the development and execution of reinforcement learning agents. It offers out-of-the-box support for popular algorithms such as PPO, A2C, DDPG and SAC, combined with high-throughput vectorized environment management. Users can easily configure policy networks, customize training loops and leverage GPU acceleration for large-scale experiments. The library’s modular design ensures seamless integration with OpenAI Gym environments, enabling researchers and practitioners to prototype, benchmark and deploy agents across a variety of control, game and simulation tasks.

defaultmodeAGENT is a Python-based framework designed to simplify the creation of intelligent agents that perform multi-step workflows autonomously. It features default-mode planning—an adaptive strategy for deciding when to explore versus exploit—alongside seamless integration of custom tools and APIs. Agents maintain conversational memory, support dynamic prompting, and offer logging for debugging. Built on top of OpenAI’s API, it allows rapid prototyping of assistants for data extraction, research, and task automation.

GPA-LM is a Python-based framework designed to simplify the creation and orchestration of AI agents powered by large language models. It features a planner that breaks down high-level instructions into sub-tasks, an executor that manages tool calls and interactions, and a memory module that retains context across sessions. The plugin architecture allows developers to add custom tools, APIs, and decision logic. With multi-agent support, GPA-LM can coordinate roles, distribute tasks, and aggregate results. It integrates seamlessly with popular LLMs like OpenAI GPT and supports deployment on various environments. The framework accelerates the development of autonomous agents for research, automation, and application prototyping.

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.

HFO_DQN combines Python and TensorFlow to deliver a complete pipeline for training soccer agents using Deep Q-Networks. Users can clone the repository, install dependencies including the HFO simulator and Python libraries, and configure training parameters in YAML files. The framework implements experience replay, target network updates, epsilon-greedy exploration, and reward shaping tailored for the half field offense domain. It features scripts for agent training, performance logging, evaluation matches, and plotting results. Modular code structure allows integration of custom neural network architectures, alternative RL algorithms, and multi-agent coordination strategies. Outputs include trained models, performance metrics, and behavior visualizations, facilitating research in reinforcement learning and multi-agent systems.

InfantAgent offers a lightweight structure for designing and deploying intelligent agents in Python. It integrates with popular LLMs (OpenAI, Hugging Face), supports persistent memory modules, and enables custom tool chains. Out of the box, you get a conversational interface, task orchestration, and policy-driven decision making. The framework’s plugin architecture allows easy extension for domain-specific tools and APIs, making it ideal for prototyping research agents, automating workflows, or embedding AI assistants into applications.

LangChain is an open-source Python framework designed to accelerate development of AI-powered applications. It provides abstractions for chaining multiple language model calls (chains), building agents that interact with external tools, and managing conversation memory. Developers can define prompts, output parsers, and run end-to-end workflows. Integrations include vector stores, databases, APIs, and hosting platforms, enabling production-ready chatbots, document analysis, code assistants, and custom AI pipelines.

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.

The LLM Maze Agent framework provides a Python-based environment for building intelligent agents capable of navigating grid mazes using large language models. By combining modular environment interfaces with chain-of-thought prompt templates and heuristic planning, the agent iteratively queries an LLM to decide movement directions, adapts to obstacles, and updates its internal state representation. Out-of-the-box support for OpenAI and Hugging Face models allows seamless integration, while configurable maze generation and step-by-step debugging enable experimentation with different strategies. Researchers can adjust reward functions, define custom observation spaces, and visualize agent paths to analyze reasoning processes. This design makes LLM Maze Agent a versatile tool for evaluating LLM-driven planning, teaching AI concepts, and benchmarking model performance on spatial reasoning tasks.

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.

MARO (Multi-Agent Resource Optimization) is a Python-based framework designed to support the development and evaluation of multi-agent reinforcement learning agents in supply chain, logistics, and resource management scenarios. It includes environment templates for inventory management, truck scheduling, cross-docking, container rental, and more. MARO offers a unified agent API, built-in trackers for experiment logging, parallel simulation capabilities for large-scale training, and visualization tools for performance analysis. The platform is modular, extensible and integrates with popular RL libraries, enabling reproducible research and rapid prototyping of AI-driven optimization solutions.

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.

MGym is a specialized framework for crafting and managing multi-agent reinforcement learning (MARL) environments in Python. It enables users to define complex scenarios with multiple agents, each having customizable observation and action spaces, reward functions, and interaction rules. MGym supports both synchronous and asynchronous execution modes, providing parallel and turn-based agent simulations. Built with a familiar Gym-like API, MGym seamlessly integrates with popular RL libraries such as Stable Baselines, RLlib, and PyTorch. It includes utility modules for environment benchmarking, result visualization, and performance analytics, facilitating systematic evaluation of MARL algorithms. Its modular architecture allows rapid prototyping of cooperative, competitive, or mixed-agent tasks, empowering researchers and developers to accelerate MARL experimentation and research.

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.

Nuzon-AI provides a Python-based agent framework that lets you define tasks, manage conversational memory, and extend capabilities via plugins. It supports integration with major LLMs (OpenAI, local models), enabling agents to perform web interactions, data analysis, and automated workflows. The architecture includes a skill registry, tool invocation system, and multi-agent orchestration layer, allowing you to compose agents for customer support, research assistance, and personal productivity. With configuration files, you can tailor each agent’s behavior, memory retention policy, and logging for debugging or audit purposes.