tsinghua-fib-lab/AgentSociety

Health v2 · maintenance only

Adoption not part of the score

1236 stars · 207 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

AgentSociety is an LLM-native agent simulation framework for building large-scale multi-agent simulations of social and urban environments. It supports social science research with pluggable environments, multiple agent reasoning patterns, and experiment workflows.

Use cases

• simulate a society of LLM agents in a city environment
• run agent-based modeling experiments for social science research
• build multi-agent simulations with LLM-driven reasoning
• test social science hypotheses with simulated populations
• compare agent reasoning patterns like ReAct and plan-execute
• model urban mobility and crowd behavior with intelligent agents

When to choose

• you need LLM-driven multi-agent social or urban simulations
• you are a researcher doing computational social science experiments
• you want a Python framework with pluggable environments and reasoning patterns

When to avoid

• you need lightweight, non-LLM agent-based modeling at massive scale
• you want a general-purpose game or robotics simulator
• you need production multi-agent orchestration for business workflows

Facets

framework · maturity active

agent-framework simulation llm-inference machine-learning artificial-intelligence simulation social-media python cross-platform llm-agents social-simulation agent-based-modeling social-science urban-simulation multi-agent-systems ai-agents research

Member repositories

For agents

markdown · JSON · MCP: product_card(name="tsinghua-fib-lab/AgentSociety")