An LLM agent runs tools in a loop to achieve a goal. An intelligent agent is an application that can perceive and understand its environment and use tools to achieve its goals. An LLM (Leveled Model) can dynamically guide its own processes and tool usage, maintaining control over how tasks are accomplished. Agents are designed to handle certain tasks more flexibly, with decisions made by the model rather than predefined rules. Leveraging CodeAct's LLM agents, OpenHands demonstrates significant advantages through ... Read Full Text
A mature agent system must provide external control interfaces without interfering with the agent's autonomous decision making. For example, users may need to pause tasks to adjust parameters, terminate execution upon detecting errors, or even switch agent roles mid task. This full lifecycle controllability requires the workflow layer to design flexible state machines and event triggered mechanisms to find a perfect balance between autonomy and controllability. It is the core controller in the OpenHands framework ... Read Full Text
Large models are uncontrollable. It's not about 'giving an LLM a bunch of tools and letting it run wild,' but rather about largely consisting of deterministic code, subtly integrating LLM capabilities at key decision points. A good agent application is a sophisticated combination of engineering design and AI capabilities, not a blind relinquishment of AI power. Within the OpenHands intelligent framework ecosystem, CodeActAgent occupies a central position, serving as the core agent module built upon the CodeAct ... Read Full Text
If the ReAct paradigm is the "brain thinking mode" of the agent, then the event driven architecture is the "neural network" of the agent system. It uses a publish subscribe pattern to coordinate the efficient operation of various components in a decentralized manner, allowing loosely coupled communication between components. The core of the entire system is not rigid synchronous calls, but an "event stream" that carries all key activities. All kinds of core operations in the system are abstracted into standardized ... Read Full Text
"A ChatBot is just something that can talk; an Agent is something that can use tools to get things done." Large Language Models (LLMs) are essentially text generators; they cannot directly operate systems, call APIs, or access databases. All of these capabilities require additional engineering implementation. The Agent tool usage model is the core architectural paradigm that breaks through the inherent limitations of Large Language Models (LLMs) and enables agents to interact with the real world. Its essence is to ... Read Full Text
Meaningful multi turn dialogues require agents to understand context. Like humans, agents need to remember the history of the conversation: what has been said and done, in order to maintain coherence and avoid repetition. Below is a sample diagram of OpenHands Applications. This article will show you how the session and interaction work. Because this series draws on a large number of articles, there may be some articles missing from the references. If so, please point them out. ... Read Full Text
This article continues the explanation of runtime, mainly introducing three components: plugins, execution system, and environment. Because this series draws on a large number of articles, there may be some articles missing from the references. If so, please point them out. ... Read Full Text
Large models are evolving from generation tools into intelligent agents with long term interaction capabilities, which places higher demands on "memory ability" because the "memory ability" of large models determines how far they can go. From single round question and answer to multi round collaboration, from general assistants to vertical agents, the core is "whether they can remember key information and anchor core goals"—only with breakthroughs in memory can AI "continuously accompany" users, which is essential ... Read Full Text
Many agent systems employ a multi agent architecture, dividing the system into different sub modules/sub agents, each with its own specific function, while a central scheduling agent manages the entire lifecycle. This modular architecture allows complex tasks to be broken down and assigned to the modules best suited for each sub task, leveraging the strengths of each model and avoiding the weaknesses of a single model in certain tasks. In OpenHands, are essentially a set of tailored instruction modules. Their core ... Read Full Text
Google's white paper provides a concise and practical definition of an Agent: . This adds a deployment runtime layer, which is different from most current definitions of AI Agents ( ). Therefore, the importance of runtime is evident. In OpenHands, the Runtime is what truly brings AI ideas to life. It's like a mobile laboratory: four walls separate the mainframe world, but leave the Agent with a complete control panel (files, terminals, network). The Agent simply hands over a slip of paper filled with instructions, ... Read Full Text
CodeAct is the cornerstone of OpenHands. CodeAct = "Using executable code to perform all actions," treating executable code as the core form of action. It allows LLM to replace traditional text or JSON style tool calls with a "write code run code see results" loop to further accomplish complex tasks. It upgrades LLM from "text interaction" to "script interaction," enabling closed loop feedback, unified tools, externalized reasoning, and frictionless expansion. In addition, Manus also uses CodeAct. Hopefully, this ... Read Full Text
This article interprets the OpenHands server in conjunction with the official documentation, which is the foundation of the OpenHands system. Because this series draws on a large number of articles, there may be some articles missing from the references. If so, please point them out. ... Read Full Text
When analyzing a system, the startup section and typical user scenarios are ideal entry points because these two sections can cover most of the system's functional modules, allowing for in depth analysis of the architecture. Because this series draws on a large number of articles, there may be some articles missing from the references. If so, please point them out. ... Read Full Text
Mastering the underlying logic of Agents is not only fundamental to their proficiency but also crucial for their design, evaluation, and scaling. For product managers, AI engineers, and technology decision makers, only a deep understanding of the Agent's technical roadmap allows for precise strategic planning in the implementation of AI applications and seizing future opportunities. We aim to delve into the following key questions from the ground up: What core technology modules are needed to build a practical AI ... Read Full Text