ZJU-LLMs/Agent-Kernel
A MicroKernel Multi-Agents System Framework for Adaptive Social Simulation Powered by LLMs
This framework helps researchers, sociologists, and urban planners create complex virtual societies to observe behaviors. You feed in rules and parameters for individual 'agents' (like people or rats), and it simulates their interactions and the resulting large-scale social dynamics. It's designed for anyone studying collective intelligence, population dynamics, or social structures.
313 stars.
Use this if you need to build and run large-scale simulations of social systems to test hypotheses about collective behavior, resource allocation, or societal evolution.
Not ideal if you're looking for a simple simulation of individual agent interactions or a non-adaptive, fixed-parameter model.
Stars
313
Forks
31
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/ZJU-LLMs/Agent-Kernel"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
openai/openai-agents-python
A lightweight, powerful framework for multi-agent workflows
openagents-org/openagents
OpenAgents - AI Agent Networks for Open Collaboration
vamplabAI/sgr-agent-core
Schema-Guided Reasoning (SGR) has agentic system design created by neuraldeep community
BrainBlend-AI/atomic-agents
Building AI agents, atomically
camel-ai/camel
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents....