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.

agent-steps is a Python step orchestration framework designed to streamline the development of AI agents by breaking complex tasks into discrete, reusable steps. Each step encapsulates a specific action—such as invoking a language model, performing data transformations, or external API calls—and can pass context to subsequent steps. The library supports synchronous and asynchronous execution, enabling scalable pipelines. Built-in logging and debugging utilities provide transparency into step execution, while its modular architecture promotes maintainability. Users can define custom step types, chain them into workflows, and integrate them easily into existing Python applications. agent-steps is suitable for building chatbots, automated data pipelines, decision support systems, and other multi-step AI-driven solutions.

AI-Agent is an extensible Python framework designed to create autonomous agents powered by OpenAI's GPT models and LangChain. It includes modules for web searching, Wikipedia lookup, calculator functions, and custom tool integrations, enabling automated research, data analysis, and script execution. Users can configure agents to plan multi-step tasks, interact with APIs, generate reports, and perform complex workflows without manual intervention, streamlining productivity across development, data science, and business processes.

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.

ModelScope Agent provides a modular, Python‐based framework to orchestrate autonomous AI agents. It features plugin integration for external tools (APIs, databases, search), conversation memory for context preservation, and customizable agent chains to handle complex tasks such as knowledge retrieval, document processing, and decision support. Developers can configure agent roles, behaviors, and prompts, as well as leverage multiple LLM backends to optimize performance and reliability in production.

CodeFuse-muAgent is a Python-based open-source framework that orchestrates multiple autonomous AI agents to collaboratively solve complex tasks. Developers define individual agents with specialized skills—such as data processing, natural language understanding, or external API interaction—and configure communication protocols for dynamic task delegation. The framework provides centralized memory management, logging, and monitoring, while remaining model-agnostic, supporting integration with popular LLMs and custom AI models. By leveraging CodeFuse-muAgent, teams can build modular AI workflows, automate multi-step processes, and scale deployments across diverse environments. Flexible configuration files and extensible APIs enable rapid prototyping, testing, and fine-tuning, making it suitable for use cases in customer support, content generation pipelines, research assistants, and more.

CUPCAKE AGI (Composable Utilitarian Pipeline for Creative, Knowledgeable, and Evolvable Autonomous General Intelligence) is a flexible Python framework that simplifies building autonomous agents by combining language models, memory, and external tools. It offers core modules including a goal planner, a model executor, and a memory manager to retain context across interactions. Developers can extend functionality via plugins to integrate APIs, databases, or custom toolkits. CUPCAKE AGI supports both synchronous and asynchronous workflows, making it ideal for research, prototyping, and production-grade agent deployments across diverse applications.

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.