百科.dev
全部条目在线工具AI 编程趋势榜开源项目技术资讯提交条目
登录
< 返回工具列表
A

Agentopia

> 编程语言
开源

Agentopia 中文 | 英文 | 日文 | 韩文 Agentopia 是一个用于在多代理社会中进行长期生命模拟的框架。Agentopia 可以模拟人类、机器人、动物、植物、病毒、微生物等各种代理的行为。

200 stars0 点赞2 次浏览
访问官网GitHub

工具介绍

Agentopia 中文 | 英文 | 日文 | 韩文 Agentopia 是一个用于在多代理社会中进行长期生命模拟的框架。Agentopia 可以模拟人类、机器人、动物、植物、病毒、微生物等各种代理的行为。

Agentopia

English | 简体中文 | 日本語 | 한국어

Agentopia is a framework for long-term life simulation in multi-agent societies. Agentopia simulates human social life across years: In our experiments, 100 agents autonomously take part in social life over 10 simulated years. They set and pursue their own goals, develop and fulfill their needs, and interact with other agents to build relationships within the society.

It is built around two questions: can we build an AI agent society where agents effectively simulate human life, and can experience and rewards from such a society improve LLMs' capabilities? To the latter end, we define a life reward that mirrors human well-being — social standing, subjective fulfillment, and economic status — and use it to train large language models, improving their anthropomorphism and role-playing ability.


Overview

Agentopia simulates human social life at the scale of years. Each agent:

  • Sets and pursues personal goals, develops skills, and engages in economic activities
  • Develops and fulfills needs across mood, material, and social dimensions
  • Interacts with other agents to build relationships within the society
  • Manages its long-term memory along the way
  • Lives through a weekly cycle: Plan → Contact → Activity → Review
  • At each year-end, updates its profile, applies for new careers, and receives a life reward reflecting social standing, subjective fulfillment, and economic status

An environment model (a capable LLM) serves as the generative engine orchestrating the simulation — verifying agent responses, providing feedback, and scheduling events — without hard-coded rules.

Repository Structure

…

Getting Started

1. Install dependencies

bash
pip install -r requirements.txt

2. Configure

bash
cp config.example.json config.json

Edit config.json:

  • Set world.name to the world you want to run (e.g. apartment, school)
  • Set role_model and god_model to model names defined in models
  • Fill in API keys and endpoints for the models you want to use
  • Adjust world.time.n_year to control the length of the simulation
  • Set fallback_model to a model used if the primary call fails (e.g., the response cannot be correctly parsed)
  • Tune max_concurrency to control the maximum number of parallel LLM requests

3. Run a simulation

bash
python scripts/run_world.py

To override the world at runtime:

bash
python scripts/run_world.py --world apartment

Model Configuration

Agentopia supports multiple LLM backends. Configure them in config.json under models:

Backend Required fields
OpenAI-compatible (vLLM, local) url, api_key, vllm_model_name
Anthropic (Claude) api_key, anthropic_model_name
Google Gemini (Vertex AI) credentials_file, project, location
Azure OpenAI url, api_key, api_version

For thinking-capable models served via vLLM, set "enable_thinking": true in the model config.

Simulation Data Layout

Each run gets its own directory under data/, named worldname_MMDDHHMM (e.g. school_06031205). On start it is copied from the base world (e.g. data/school/), then all simulation output is written into it. Data is append-only JSONL except for profiles and config files.

…

Life Reward Training

A primary goal of Agentopia is to improve the anthropomorphic role-playing ability of LLMs through social simulation. To that end, scripts/build_rft_data.py selects, from a finished simulation, the high-advantage trajectories (see Section 4 of the paper) and packages them into training data. It measures agents' life-reward and calculates returns and advantages, selects the highest-advantage trajectories, and collects their generation traces into a training set.

bash
python scripts/build_rft_data.py --data-dir school_06031205 --top 0.25 

Key arguments:

  • --data-dir (required): a specific simulation run directory under data/, named worldname_ (e.g. school_06031205) — not the base world name school.
  • --top: fraction of top trajectories to keep per period (defaults to world.reward.rft_top_fraction in config.json).
  • --n-year: restrict selection to the first N simulated years.

Outputs (under rft_data/):

  • rft_data/_YW.jsonl — training samples
  • rft_data/_YW.md — statistics report on the selected training samples
  • rft_data/god__YW.jsonl — sampled environment-model generation data (only if data//god/ exists)

Analysis Skills

The repo ships a set of Claude Code skills under .claude/skills/ for inspecting a finished run. When working in Claude Code, invoke a skill by name (e.g. analyze run school_06031205); each skill also lists trigger phrases in its SKILL.md frontmatter.

Skill What it does
analyze-run Qualitative deep-dive into a run — agent experiences, inner journey, personality growth — producing system-level and per-agent reports under data//run_analysis/.
run-metrics Quantitative metrics for a run (tokens, contacts, activities, spending, skills, fulfillment, social eval). Wraps scripts/compute_metrics.py; writes analysis/results/_metrics.json.
analyze-activity Checks whether agents' activity-phase utterances read like a real human, against the criteria in analyze-activity/PRINCIPLES.md. Uses scripts/extract_activity_dialogues.py.
time-analysis Reports per-week wall-clock time consumed by a run, parsed from logs//world.log. Wraps scripts/time_analysis.py.

These skills are optional analysis helpers; they are not required to run a simulation.

License

This project is released under the MIT License.

Issues· 3 开放

查看全部 Issues在 GitHub 打开

暂无开放 Issues,或尚未同步最近议题。

> 标签

Python

暂无评论,来聊聊你的看法吧

> 工具信息

发布日期2026年8月1日
最后更新2026年9月18日
分类编程语言
定价开源

> 相关工具

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言