Ji-Cather/GraphAgent
Code for ACL25-findings. An LLM-based agent simulation framework that simulates human behavior and generates dynamic, text-based social graphs.
This project helps social scientists, network scientists, and market researchers understand human interactions by simulating dynamic social networks. You provide a prompt describing the kind of network you want (e.g., tweet, movie rating, or citation networks), and it generates a text-attributed social graph. This allows you to observe how different behaviors and network structures emerge over time.
Use this if you need to generate realistic, dynamic social network data to study human behavior in online communities, e-commerce, or academic collaboration scenarios.
Not ideal if you're looking for a simple, out-of-the-box tool without any setup, or if you don't have access to an LLM API key.
Stars
91
Forks
11
Language
HTML
License
—
Category
Last pushed
Oct 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Ji-Cather/GraphAgent"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
patterns-ai-core/langchainrb
Build LLM-powered applications in Ruby
3uyuan1ee/Fix_agent
基于 LangChain1.0和DeepAgents的代码优化Agent
FareedKhan-dev/Multi-Agent-AI-System
Building a Multi-Agent AI System with LangGraph and LangSmith
tadata-org/langchain-runner
Zero-configuration way to expose LangChain/LangGraph agents as autonomous services with...
skygazer42/GustoBot
五星大厨:全面Multi-Agent 的客服机器人，基于langraph实现，txt2sql ,txt2cypher, lightrag, 多模态 等