CogAgent is a research-oriented, open-source Python library designed to streamline the development of AI agents. It provides core modules for memory management, planning and reasoning, tool and API integration, and chain-of-thought execution. With its highly modular architecture, users can define custom tools, memory stores, and agent policies to create conversational chatbots, autonomous task planners, and workflow automation scripts. CogAgent supports integration with popular LLMs such as OpenAI GPT and Meta LLaMA, allowing researchers and developers to experiment, extend, and scale their intelligent agents for a variety of real-world applications.

Stella Framework empowers developers to build robust AI agents that can maintain context, perform tool-assisted actions, and deliver dynamic conversational experiences. By abstracting the complexities of LLM integrations, Stella offers provider-agnostic adapters for OpenAI, Hugging Face, and self-hosted models. Agents can leverage customizable memory stores to recall user data and conversation history, and plugins enable interactions with external APIs, databases, or services. The built-in orchestration engine manages decision loops, while a concise DSL allows defining actions, tool calls, and response handling. Whether creating customer support bots, research assistants, or workflow automators, Stella provides a scalable foundation for deploying production-grade AI agents.

AI Agents offers a structured toolkit for developers to build autonomous agents using large language models. It includes modules for integrating external APIs, managing conversational or long-term memory, orchestrating multi-step workflows, and chaining LLM calls. The framework provides templates for common agent types—data retrieval, question answering, and task automation—while allowing customization of prompts, tool definitions, and memory strategies. With asynchronous support, plugin architecture, and modular design, AI Agents enables scalable, maintainable, and extendable agentic applications.

AgentKit is a powerful platform for creating bespoke AI agents tailored to specific business needs. It allows users to design workflows and automate repetitive tasks easily without needing extensive programming knowledge. With its intuitive interface, users can integrate various APIs, streamline processes, and enhance productivity by building agents that act on behalf of users. This innovative tool empowers businesses to leverage AI technology for smoother operations and improved performance.

Agent of Code is a versatile AI agent framework enabling developers to offload routine coding tasks to intelligent agents. It leverages large language models to translate natural language prompts into fully functional code, perform automated code reviews, debug existing code, and refactor legacy codebases. Users define agent goals and parameters through YAML or JSON configurations, select plugins for tasks like testing or CI integration, and execute agents via CLI. The framework orchestrates API calls, manages context windows, and assembles modular responses into cohesive code scripts. With an extensible architecture, developers can plug in custom modules, integrate with version control, and tailor the agent pipeline to project workflows.

Agentic Kernel offers a decoupled architecture for constructing AI agents by composing reusable components. Developers can define planning pipelines to break down goals, configure short-term and long-term memory stores using embeddings or file-based backends, and register external tools or APIs for action execution. The framework supports dynamic tool selection, agent reflection cycles, and built-in scheduling to manage agent workflows. Its pluggable design accommodates any LLM provider and custom components, enabling use cases such as conversational assistants, automated research agents, and data-processing bots. With transparent logging, state management, and easy integration, Agentic Kernel accelerates development while ensuring maintainability and scalability in AI-driven applications.

AI Agent Demo provides a versatile template for constructing AI agents that can interact with users and external data sources. It leverages LangChain to orchestrate chains, tools, and memory modules, enabling the agent to perform tasks such as web searches via SerpAPI, summarize web content, maintain conversation history with vector-based memory, and execute code snippets through a secure Python REPL tool. The agent exposes CLI commands and HTTP endpoints via FastAPI, supporting both text and voice input. Developers can customize tool definitions and chain logic to tailor agents for customer support, data retrieval, or automated workflows. The modular architecture simplifies integration of new capabilities like database queries or third-party APIs.

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.

js-agent provides developers with a minimalistic yet powerful toolkit to create autonomous AI agents in JavaScript. It offers abstractions for conversation memory, function-calling tools, customizable planning strategies, and error handling. With js-agent, you can quickly wire up prompts, manage state, invoke external APIs, and orchestrate complex agent behaviors through a simple, modular API. It's designed to run in Node.js environments and integrates seamlessly with the OpenAI API to power intelligent, context-aware agents.

LaVague is an open-source framework designed for building and deploying web agents quickly and efficiently. Users can create various agents that automate tasks across web applications, from data entry to comprehensive information retrieval. The framework supports integration with local models, such as Llama 3 8b, making it a versatile choice for enterprises looking to enhance their operations with AI-driven automation. With LaVague, developers can adapt agents to fit specific workflows, enhancing productivity and efficiency.

Micro-agent is a lightweight, unopinionated JavaScript library designed to simplify the creation of sophisticated AI agents using large language models. It exposes core abstractions such as agents, tools, planners, and memory stores, allowing developers to assemble custom conversational flows. Agents can invoke external APIs or internal utilities as tools, enabling dynamic data retrieval and action execution. The library supports both short-term conversational memory and long-term persistent memory to maintain context across sessions. Planners orchestrate chain-of-thought processes, breaking down complex tasks into tool calls or language model queries. With configurable prompt templates and execution strategies, micro-agent adapts seamlessly to frontend web applications, Node.js services, and edge environments, providing a flexible foundation for chatbots, virtual assistants, or autonomous decision-making systems.

Neocortex is a web-based AI platform that acts as a personal knowledge hub and task manager. It stores and retrieves information using long-term memory, creates intelligent agents to handle research, summarization, and planning tasks, and integrates with documents, calendars, and APIs. Users can interact via chat to query past insights, generate reports, and delegate workflows to custom agents. Neocortex continually refines context, offers proactive reminders, and supports collaboration across teams.

SCOUT-2 provides a modular architecture for building autonomous agents powered by large language models. It includes goal decomposition, task planning, an execution engine, and a feedback-driven reflection module. Developers define a top-level objective, and SCOUT-2 automatically generates a task tree, dispatches worker agents for execution, monitors progress, and refines tasks based on outcomes. It integrates with OpenAI APIs and can be extended with custom prompts and templates to support a wide range of workflows.

Swarm Simulator provides a customizable environment for real-time multi-agent experiments. Users can adjust key behavior parameters—alignment, cohesion, separation—and observe emergent dynamics on a visual canvas. It supports interactive UI sliders, dynamic agent count adjustment, and data export for analysis. Ideal for educational demonstrations, research prototyping, or hobbyist exploration of swarm intelligence principles.

Tiny-OAI-MCP-Agent provides a small, extensible agent architecture built on the OpenAI API. It implements a multi-cognitive process (MCP) loop for reasoning, memory, and tool usage. You define tools (APIs, file operations, code execution), and the agent plans tasks, recalls context, invokes tools, and iterates on results. This minimal codebase allows developers to experiment with autonomous workflows, custom heuristics, and advanced prompt patterns while handling API calls, state management, and error recovery automatically.