# D2I-CUHKSZ/MicroWorld

Repository: https://github.com/D2I-CUHKSZ/MicroWorld
Canonical: https://ross.abutalabs.com/products/microworld
Homepage: https://d2i-cuhksz.github.io/MicroWorld/
Language: Python
License: AGPL-3.0
License Family: copyleft
Last push: 2026-06-02T14:21:57+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 85, release rhythm 35, longevity 11
- inputs: {"age_days": 161, "days_push": 92, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1039, forks 91 (observed 2026-08-28T04:03:20.071364+00:00)

## What it is
MicroWorld is a lightweight Python engine that turns multi-modal event materials (documents, images, videos, graph signals) into structured event graphs, agent populations, and runnable multi-agent social simulations. It keeps all intermediate artifacts—graphs, prompts, traces, memory states, and reports—inspectable within the same run.

## Use cases
- simulate how a news story spreads and evolves on social platforms
- build agent populations from event documents and media
- run multi-agent LLM discussions over an event graph
- study opinion dynamics with topology-aware influence
- reduce token costs in large-scale agent simulations
- inspect agent memory and action traces after a simulation run
- convert multimodal event material into knowledge graphs

## When to choose
- you need inspectable, evidence-traceable social simulations rather than just a final report
- you want multi-modal (text, image, video, graph) ingestion into one simulation pipeline
- token efficiency matters for large agent populations
- you are researching information diffusion, hype cycles, or platform dynamics

## When to avoid
- you need a battle-tested production system rather than a research tool
- you want simple agent-based modeling without LLM or multimodal components
- you require non-Python environments or real-time interactive simulation

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, machine-learning, nlp, data-visualization, etl, llm-inference
- domain: artificial-intelligence, simulation, social-media, data-science
- platform: python, cross-platform, cli
- tags: social-simulation, multi-agent, event-graph, multimodal-ingestion, topology-aware, ppr-influence, agent-based-modeling, llm-agents, opinion-dynamics, ai-agents, natural-language-processing, research

## Member repositories
- D2I-CUHKSZ/MicroWorld (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:20.071364+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:03:33.005124+00:00, confidence not recorded.
  - readme: https://github.com/D2I-CUHKSZ/MicroWorld (fetched 2026-08-28T04:03:20.071364+00:00, sha 7fc0fdf0e7eb)
  - homepage: https://d2i-cuhksz.github.io/MicroWorld/ (fetched 2026-08-29T13:04:40.760932+00:00, sha fd3d419b4815)
- Data as of 2026-08-30T08:39:29.467469+00:00.