Mina provides a lightweight yet powerful foundation for constructing AI agents in Python. You can define custom tools (such as web scrapers, calculators, or database connectors), attach memory buffers to maintain conversational context, and orchestrate sequences of calls to language models for multi-step reasoning. Built on top of common LLM APIs, Mina handles asynchronous execution, error handling, and logging out of the box. Its modular design makes it easy to extend with new capabilities, while the CLI interface enables quick prototyping and deployment of agent-driven applications.

NavGround Learning provides a comprehensive toolkit for developing and benchmarking reinforcement learning agents in navigation tasks. It supports multi-agent simulation, collision modeling, and customizable sensors and actuators. Users can select from predefined policy templates or implement custom architectures, train with state-of-the-art RL algorithms, and visualize performance metrics. Its integration with OpenAI Gym and Stable Baselines3 simplifies experiment management, while built-in logging and visualization tools allow in-depth analysis of agent behavior and training dynamics.

Swarms operates as a Python-first framework and web-based interface, empowering users to configure individual agents with specific roles, memory management, and custom prompts. Users define agent interactions through a visual flow builder or YAML configuration, orchestrating complex decision trees, debates, and collaborative tasks. The platform supports plugin integration for data querying, knowledge base access, and third-party API calls. Upon deployment, Swarms provides real-time monitoring of agent activities, performance metrics, and logs. It scales horizontally using container orchestration tools, enabling large-scale AI simulations, robotic control architectures, or intelligent workflow automations. The open-source architecture ensures extensibility, community-driven enhancements, and self-hosting options for full data control.

WanderMind provides a modular architecture for building self-guided AI agents. It manages a persistent memory store to retain context across sessions, integrates with external tools and APIs for extended functionality, and orchestrates multi-step reasoning through customizable planners. Developers can plug in different LLM providers, define asynchronous tasks, and extend the system with new tool adapters. This framework accelerates experimentation with autonomous workflows, enabling applications from idea exploration to automated research assistants without heavy engineering overhead.

Doraemon-Agent is an open-source Python platform and framework designed for developers to build sophisticated AI agents. It allows you to integrate custom plugins and external tools, maintain long-term memory across sessions, and execute chain-of-thought planning with multiple steps. Developers can configure agent roles, manage context, log interactions, and extend functionality through a plugin architecture. It simplifies the creation of autonomous assistants for tasks like data analysis, research support, or customer service automation.

Lila delivers a complete AI agent framework tailored for multi-step reasoning and autonomous task execution. Developers can define custom tools (APIs, databases, webhooks) and configure Lila to call them dynamically during runtime. It offers memory modules to store conversation history and facts, a planning component to sequence sub-tasks, and chain-of-thought prompting for transparent decision paths. Its plugin system allows seamless extension with new capabilities, while built-in monitoring tracks agent actions and outputs. Lila’s modular design makes it easy to integrate into existing Python projects or deploy as a hosted service for real-time agent workflows.

LLM Agents Example provides a hands-on codebase for building AI agents in Python. It demonstrates registering custom tools (web search, math solver via WolframAlpha, CSV analyzer, Python REPL), creating chat and retrieval-based agents, and connecting to vector stores for document question answering. The repo illustrates patterns for maintaining conversational memory, dispatching tool calls dynamically, and chaining multiple LLM prompts to solve complex tasks. Users learn how to integrate third-party APIs, structure agent workflows, and extend the framework with new capabilities—serving as a practical guide for developer experimentation and prototyping.

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.

AI-Agents provides a flexible agent architecture that orchestrates language model planners, persistent memory modules, and pluggable toolkits. Developers define tools for HTTP requests, file operations, and custom logic, then configure an LLM planner to decide which tool to invoke. Memory stores context and conversation history. The framework handles asynchronous execution, error recovery, and logging, enabling rapid prototyping of intelligent assistants, data analyzers, or automation bots without reinventing core orchestration logic.

Build with ADK streamlines the creation of AI agents by providing a CLI scaffolding tool, workflow definitions, LLM integration modules, testing utilities, logging, and deployment support. Developers can initialize agent projects, select AI models, configure prompts, connect external tools or APIs, run local tests, and push their agents to production or container platforms—all with simple commands. The modular architecture allows easy extension with plugins and supports multiple programming languages for maximum flexibility.

Chipper is a fully open-source React component library designed to simplify the creation of conversational interfaces powered by large language models. It offers real-time streaming of AI responses, built-in context and history management, support for multiple agents in a single chat, file attachments, and theme customization. Developers can integrate any LLM backend via simple props, extend with plugins, and style using CSS-in-JS for seamless branding and responsive layouts.

Fetch.ai is an open-source platform and software development kit designed for building autonomous agents that represent digital twins on a decentralized network. It provides a Python and Rust SDK, an Open Economic Framework (OEF) for peer discovery, and seamless integration with its ledger for secure transactions. Developers can define custom agent skills—such as market making, data provision, or task bidding—and deploy them to testnets or mainnets. Fetch.ai agents autonomously communicate, negotiate, and execute smart contracts, enabling powerful multi-agent coordination for supply chains, IoT ecosystems, mobility services, energy grids, and beyond.

JaCaMo provides a unified environment for designing and running multi-agent systems (MAS) by integrating three core components: the Jason agent programming language for BDI-based agents, CArtAgO for artifact-based environmental modeling, and Moise for specifying organizational structures and roles. Developers can write agent plans, define artifacts with operations, and organize groups of agents under normative frameworks. The platform includes tooling for simulation, debugging, and visualization of MAS interactions. With support for distributed execution, artifact repositories, and flexible messaging, JaCaMo enables rapid prototyping and research in areas like swarm intelligence, collaborative robotics, and distributed decision-making. Its modular design ensures scalability and extensibility across academic and industrial projects.

FMAS (Flexible Multi-Agent System) is an open-source Python library for building, running, and visualizing multi-agent simulations. You can define agents with custom decision logic, configure an environment model, set up messaging channels for communication, and execute scalable simulation runs. FMAS provides hooks for monitoring agent state, debugging interactions, and exporting results. Its modular architecture supports plugins for visualization, metrics collection, and integration with external data sources, making it ideal for research, education, and real-world prototypes of autonomous systems.

GenAI Agents SDK is an open-source Python library designed to help developers create self-driven AI agents using large language models. It offers a core agent template with pluggable modules for memory storage, tool interfaces, planning strategies, and execution loops. You can configure agents to call external APIs, read/write files, run searches, or interact with databases. Its modular design ensures easy customization, rapid prototyping, and seamless integration of new capabilities, empowering the creation of dynamic, autonomous AI applications that can reason, plan, and act in real-world scenarios.