AppAgent is an LLM-based multimodal agent framework designed to operate smartphone applications without manual scripting. It integrates screen capture, GUI element detection, OCR parsing, and natural language planning to understand app layouts and user intents. The framework issues touch events (tap, swipe, text input) through an Android device or emulator to automate workflows. Researchers and developers can customize prompts, configure LLM APIs, and extend modules to support new apps and tasks, achieving adaptive and scalable mobile automation.

Autonomais is a modular AI agent framework designed for full autonomy in task planning and execution. It integrates large language models to generate plans, orchestrates actions via a customizable pipeline, and stores context in memory modules for coherent multi-step reasoning. Developers can plug in external tools like web scrapers, databases, and APIs, define custom action handlers, and fine-tune agent behavior through configurable skills. The framework supports logging, error handling, and step-by-step debugging, ensuring reliable automation of research tasks, data analysis, and web interactions. With its extensible plugin architecture, Autonomais enables rapid development of specialized agents capable of complex decision-making and dynamic tool usage.

ggfai provides a unified interface to define goals, manage multi-step reasoning, and maintain conversational context with memory modules. It supports customizable tool integrations for calling external services or APIs, asynchronous execution flows, and abstractions over OpenAI GPT models. The framework’s plugin architecture lets you swap memory backends, knowledge stores, and action templates, simplifying agent orchestration across tasks like customer support, data retrieval, or personal assistants.

CamelAGI is an open-source framework designed to simplify the creation of autonomous AI agents. It features a plugin architecture for custom tools, long-term memory integration for context persistence, and support for multiple large language models such as GPT-4 and Llama 2. Through explicit planning and execution modules, agents can decompose tasks, call external APIs, and adapt over time. CamelAGI’s extensibility and community-driven approach make it suitable for research prototypes, production systems, and educational projects alike.

Layra is designed to simplify developing LLM-powered agents by providing a modular architecture that integrates with various tools and memory stores. It features a planner that breaks down tasks into subgoals, a memory module for storing conversation and context, and a plugin system to connect external APIs or custom functions. Layra also supports orchestrating multiple agent instances to collaborate on complex workflows, enabling parallel execution and task delegation. With clear abstractions for tools, memory, and policy definitions, developers can rapidly prototype and deploy intelligent agents for customer support, data analysis, RAG, and more. It is framework-agnostic toward modeling backends, supporting OpenAI, Hugging Face, and local LLMs.

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.

MiniAgent is a minimalistic open-source framework built in Python for constructing autonomous AI agents capable of planning and executing complex workflows. At its core, MiniAgent includes a task planning module that decomposes high-level goals into ordered steps, an execution controller that runs each step sequentially, and built-in adapters for integrating external tools and APIs, including web services, databases, and custom scripts. It also features a lightweight memory management system to persist conversational or task context. Developers can easily register custom action plugins, define policy rules for decision-making, and extend tool functionality. With support for OpenAI models and local LLMs, MiniAgent enables rapid prototyping of chatbots, digital workers, and automated pipelines, all under an MIT license.

Nagato AI is an extensible AI agent framework that orchestrates autonomous workflows by combining task planning, memory management, and tool integrations. Users can define custom tools and APIs, allowing the agent to retrieve information, perform actions, and maintain conversational context over long sessions. With its plugin architecture and conversational UI, Nagato AI adapts to diverse scenarios—from research assistance and data analysis to personal productivity and automated customer interactions—while remaining fully open-source and developer-friendly.

SeeAct is designed to empower vision-language agents with a two-stage pipeline: a planning module powered by large language models generates subgoals based on observed scenes, and an execution module translates subgoals into environment-specific actions. A perception backbone extracts object and scene features from images or simulations. The modular architecture allows easy replacement of planners or perception networks and supports evaluation on AI2-THOR, Habitat, and custom environments. SeeAct accelerates research on interactive embodied AI by providing end-to-end task decomposition, grounding, and execution.

Symbol-LLM offers a modular architecture for constructing AI agents powered by large language models augmented with symbolic memory stores. It features a planner module to break down complex tasks, an executor to invoke tools, and a memory system to maintain context across interactions. With built-in toolkits like web search, calculator and code runner, plus simple APIs for custom tool integration, Symbol-LLM enables developers and researchers to rapidly prototype and deploy sophisticated LLM-based assistants for various domains including research, customer support, and workflow automation.

AgentSmithy is designed to streamline the development lifecycle of AI agents by offering modular components for memory management, task planning, and execution orchestration. The framework leverages Google Cloud Storage or Firestore for persistent memory, Cloud Functions for event-driven triggers, and Pub/Sub for scalable messaging. Handlers define agent behaviors, while planners manage multi-step task execution. Observability modules track performance metrics and logs. Developers can integrate bespoke plugins to enhance capabilities such as custom data sources, specialized LLMs, or domain-specific tools. AgentSmithy’s cloud-native architecture ensures high availability and elasticity, allowing deployment across development, testing, and production environments seamlessly. With built-in security and role-based access controls, teams can maintain governance while rapidly iterating on intelligent agent solutions.

ElizaOS provides a robust suite of tools to design, test, and deploy autonomous AI agents within TypeScript projects. Developers define agent personalities, goals, and memory hierarchies, then leverage ElizaOS's planning system to outline task workflows. Its modular connector architecture simplifies integrating with communication platforms—Discord, Telegram, Slack, X—and blockchain networks via Web3 adapters. ElizaOS supports multiple LLM backends (OpenAI, Anthropic, Llama, Gemini), allowing seamless switching between models. Plugin support extends functionality with custom skills, logging, and observability features. Through its CLI and SDK, teams can iterate on agent configurations, monitor live performance, and scale deployments in cloud environments or on-premises. ElizaOS empowers companies to automate customer interactions, social media engagement, and business processes with autonomous digital workers.

IoA provides a flexible architecture for defining, coordinating, and executing multiple AI agents in a unified workflow. Key components include a planner that decomposes high-level goals, an executor that dispatches tasks to specialized agents, and memory modules for context management. It supports integration with external APIs and toolkits, real-time monitoring, and customizable skill plugins. Developers can rapidly prototype autonomous assistants, customer support bots, and data processing pipelines by combining ready-made modules or extending them with custom logic.

Isek is a developer-centric platform for building AI agents with modular architecture. It offers a plugin system for tools and data sources, built-in memory for context retention, and a planning engine to coordinate multi-step tasks. You can deploy agents locally or in the cloud, integrate any LLM backend, and extend functionality via community or custom modules. Isek streamlines the creation of chatbots, virtual assistants, and automated workflows by providing templates, SDKs, and CLI tools for rapid development.

llm-ReAct implements the ReAct (Reasoning and Acting) architecture for large language models, enabling seamless integration of chain-of-thought reasoning with external tool execution and memory storage. Developers can configure a toolkit of custom tools—such as web search, database queries, file operations, and calculators—and instruct the agent to plan multi-step tasks, invoking tools as needed to retrieve or process information. The built-in memory module preserves conversational state and past actions, supporting more context-aware agent behaviors. With modular Python code and support for OpenAI APIs, llm-ReAct simplifies experimentation and deployment of intelligent agents that can adaptively solve problems, automate workflows, and provide context-rich responses.

Nova provides a comprehensive toolkit for creating autonomous AI agents in Python. It offers a planner that decomposes goals into actionable steps, a plugin system to integrate any external tools or APIs, and a memory module to store and recall conversation context. Developers can configure custom behaviors, track agent decisions through logs, and extend functionality with minimal code. Nova streamlines the entire agent lifecycle from design to deployment.

Pillar is a comprehensive AI agent framework designed to simplify the development and deployment of intelligent multi-step workflows. It features a modular architecture with planners for task decomposition, memory stores for context retention, and executors that perform actions via external APIs or custom code. Developers can define agent pipelines in YAML or JSON, integrate any LLM provider, and extend functionality through custom plugins. Pillar handles asynchronous execution and context management out of the box, reducing boilerplate code and accelerating time-to-market for AI-driven applications such as chatbots, data analysis assistants, and automated business processes.

Whisprlist offers a unique approach to task management by leveraging voice commands to create and organize tasks. No more typing and manual input; just speak, and the AI handles the rest. It also sends a daily agenda email to highlight your focus areas and upcoming tasks. This personalized assistance helps you stay productive and organized. With a free plan and an affordable premium plan, Whisprlist makes task management effortless and efficient.

Agent-FLAN is designed to simplify the creation of sophisticated AI agent-driven applications by segmenting tasks into planning and execution roles. Users define agent behaviors and workflows via configuration files, specifying input formats, tool interfaces, and communication protocols. The planning agent generates high-level task plans, while execution agents carry out specific actions, such as calling APIs, processing data, or generating content with large language models. Agent-FLAN’s modular architecture supports plug-and-play tool adapters, custom prompt templates, and real-time monitoring dashboards. It seamlessly integrates with popular LLM providers like OpenAI, Anthropic, and Hugging Face, enabling developers to quickly prototype, test, and deploy multi-agent workflows for scenarios such as automated research assistants, dynamic content generation pipelines, and enterprise process automation.

Agentic-AI is an open-source Python framework that streamlines building autonomous agents leveraging large language models such as OpenAI GPT. It provides core modules for task planning, memory persistence, and tool integration, allowing agents to decompose high-level goals into executable steps. The framework supports plugin-based custom tools—APIs, web scraping, database queries—enabling agents to interact with external systems. It features a chain-of-thought reasoning engine coordinating planning and execution loops, context-aware memory recalls, and dynamic decision-making. Developers can easily configure agent behaviors, monitor action logs, and extend functionality, achieving scalable, adaptable AI-driven automation for diverse applications.