# XiaoLuoLYG/GOD

Govern, Observe, Direct - a real-time control room for agent societies

Repository: https://github.com/XiaoLuoLYG/GOD
Canonical: https://ross.abutalabs.com/products/xiaoluolyg-god
Homepage: https://xiaoluolyg.github.io/GOD/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent-control-room, agent-society, generative-agents, human-in-the-loop, llm-agents, multi-agent-simulation, openai-compatible, python, react, social-simulation, pixel-replay, agent, ai-agents
Last push: 2026-07-22T09:14:34+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 88, longevity 8
- inputs: {"age_days": 114, "days_push": 42, "days_rel": 83, "gap_med": 5, "n_releases_24m": 2}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1072, forks 120 (observed 2026-08-28T04:03:28.693555+00:00)

## What it is
GOD (Govern, Observe, Direct) is a real-time control room for inspecting and steering societies of LLM-powered agents, letting operators pause time, interrogate residents, and alter simulation outcomes. It pairs a Python backend with a React frontend and supports shareable, rerunnable experiment packs and browser-readable replays.

## Use cases
- run and steer a simulated town of LLM agents in real time
- pause an agent society simulation and whisper instructions to a specific agent
- replay and inspect past multi-agent simulation runs in the browser
- export experiment packs so others can reproduce the same simulation setup
- study emergent social behavior in generative agent societies
- do human-in-the-loop intervention experiments on agent populations

## When to choose
- you want interactive control over a multi-agent LLM simulation rather than passive observation
- you need reproducible, shareable agent-society experiments with inspectable replays
- you want an openai-compatible, self-hostable generative-agents platform with a web UI

## When to avoid
- you need a production multi-agent orchestration framework for building applications rather than a research/control console
- you want lightweight headless agent simulation without a web interface
- you need non-LLM or non-social agent simulations

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, simulation, chat-interface, data-visualization, llm-inference
- domain: simulation, artificial-intelligence, large-language-models
- platform: python, cross-platform
- tags: multi-agent-simulation, generative-agents, human-in-the-loop, agent-society, social-simulation, replay, openai-compatible, control-room, ai-agents, web-server

## Member repositories
- XiaoLuoLYG/GOD (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:28.693555+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 2026-08-30T06:53:40.318596+00:00, confidence not recorded.
  - readme: https://github.com/XiaoLuoLYG/GOD (fetched 2026-08-28T04:03:28.693555+00:00, sha b7a38ddb5793)
  - homepage: https://xiaoluolyg.github.io/GOD/ (fetched 2026-08-29T12:55:54.823273+00:00, sha dc757beb692d)
- Data as of 2026-08-30T08:39:29.467469+00:00.