Agent-Kernel

ZJU-LLMs/Agent-Kernel is ranked 4,274 among these 8 peers; ClickHouse/agent-skills is ranked 4,273.

Help us grow and improve by giving Agent-Kernel a 🌟 star on GitHub! This offers the opportunity to **Explore the Scaling Law of Collective Intelligence**. ✨ Highlights Agent-Kernel supports: **dynamic addition and removal of LLMs-based agents at runtime**; **unlimited scalability of agents**; **real-time intervention during the simulation process**; **trustworthy verification of agent behaviors and large model outputs**; **code reuse across different simulation scenarios**. 🎬 Showcase Agent-Kernel has been successfully applied to several complex social simulation scenarios: 1. Universe

25 Experiment Simulating the famous "Universe 25" sociological experiment to explore the relationships between population density, social structure, and behavioral anomalies. ZJU Campus Life Constructing a high-fidelity simulation of the campus environment to study pedestrian flow dynamics, resource allocation, and social interaction patterns. OpenHospital Building an interactive hospital simulation arena for evolving and benchmarking LLM-based collective intelligence in realistic clinical workflows. 📍 Table of Contents ✨ Highlights 🎬 Showcase Universe 25 Experiment ZJU Campus Life OpenHospital 🎯 Core Advantages: Why Choose Agent

-Kernel? Adaptability Configurability Reliability Reusability 🏛️ Architecture and Design Framework Overview Software Design 🚀 Quick Start Requirements Installation (Optional) Start Society-Panel 📂 Project Structure 🎓 Citation 🤝 Contributors 📜 License 🎯 Core Advantages: Why Choose Agent-Kernel? Agent-Kernel offers four core advantages for social simulation, making it stand out in the study of multi-agent systems: 1. Adaptability Agent-Kernel supports adding/removing agents, changing environments, and modifying behaviors at runtime. This enables simulations to naturally reflect population flow, environmental shifts, and evolving behavioral patterns

. Configurability With the Controller module, Agent-Kernel allows real-time adjustments to parameters or events during simulation. This makes it easy to test and validate complex sociological hypotheses. Reliability Agent-Kernel employs a strict system-level verification mechanism, validating every agent action. This ensures that simulation behaviors follow physical and social rules, maintaining scientific rigor. Reusability Agent-Kernel uses a standardized, plugin-based modular design. Codes can be reused across scenarios, significantly accelerating research iteration. The core manages plugin registration

, behavior verification, asynchronous communication, and other core responsibilities, while plugins provide the specialized functions for social simulation, as shown in the diagram below: 2. Software Design To realize the core design goals of the Agent-Kernel framework, we made a series of deliberate software design decisions, as illustrated in the diagram below: 🚀 Quick Start 1. Installation You can choose either **standalone** or **distributed** package based on your needs. Agent-Kernel Standalone 👉 For detailed usage and examples, see the Standalone README

. Agent-Kernel Distributed Note: The distributed package depends on **Ray** and will install it automatically. 👉 For detailed usage and examples, see the Distributed README. Installing with Optional Features Both and support optional dependencies for web services and storage solutions. → Installs , , → Installs , , → Installs both and To install a package with these extras, use square brackets . (Optional) Start Society-Panel Society-Panel is a web-based control panel to help you configure, deploy, and monitor your simulations visually. **Access the UI:** From

the panel, you can upload custom code packages, edit configuration files through a graphical interface, and control the simulation lifecycle.