# openai/neural-mmo

Code for the paper "Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents"

Repository: https://github.com/openai/neural-mmo
Canonical: https://ross.abutalabs.com/products/neural-mmo
Homepage: https://openai.com/blog/neural-mmo/
Language: Python
License: MIT
License Family: permissive
Topics: paper
Archived: true
Last push: 2023-07-21T13:04:40+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2743, "days_push": 1139, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1654, forks 269 (observed 2026-08-28T04:05:17.745450+00:00)

## What it is
Neural MMO is a massively multiagent game environment (MMORPG-style) for training and evaluating intelligent agents, released alongside an OpenAI research paper. It provides a persistent, open-ended simulation with thousands of concurrent agents, plus rendering and neural network experiment modules built on PyTorch.

## Use cases
- train multiagent reinforcement learning agents in a persistent open-ended environment
- research artificial life and emergent agent behavior at population scale
- benchmark multiagent RL algorithms with many concurrent learning agents
- simulate MMORPG-like ecosystems with economies and combat for AI experiments
- study exploration and niche formation among large agent populations

## When to choose
- you need a research environment with thousands of persistent, concurrently learning agents
- you want an open-ended MMORPG-style proxy for real-world complexity in RL experiments
- you are reproducing or extending the Neural MMO paper

## When to avoid
- you need maintained software - this repo is archived and active development moved to jsuarez5341/neural-mmo
- you want a polished game or production-ready simulator rather than research code
- you need a lightweight single-agent RL gym environment

## Facets
- artifact type: library
- maturity: abandoned
- function: simulation, machine-learning, reinforcement-learning, game-engine
- domain: artificial-intelligence, reinforcement-learning, simulation
- platform: python, cross-platform
- tags: multiagent, mmo, openai, research-code, archived, neural-networks, artificial-life, game-development, research, linux

## Member repositories
- openai/neural-mmo (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:17.745450+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 2026-08-30T03:44:56.471457+00:00, confidence not recorded.
  - readme: https://github.com/openai/neural-mmo (fetched 2026-08-28T04:05:17.745450+00:00, sha bf8c2be121fd)
  - homepage: https://openai.com/blog/neural-mmo/ (fetched 2026-08-29T11:18:01.655366+00:00, sha 5020686b4555)
  - site_page: https://openai.com/about (fetched 2026-08-29T11:18:01.658072+00:00, sha de4b627b33e3)
  - site_page: https://developers.openai.com/api/docs (fetched 2026-08-29T11:18:01.660008+00:00, sha d617c5215f2a)
  - site_page: https://developers.openai.com/ (fetched 2026-08-29T11:18:01.662101+00:00, sha 7d240c906018)
- Data as of 2026-08-30T08:39:29.467469+00:00.