openai/neural-mmo

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

1654 stars · 269 forks observed · 2026-08-28

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

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

library · maturity abandoned

simulation machine-learning reinforcement-learning game-engine artificial-intelligence reinforcement-learning simulation python cross-platform multiagent mmo openai research-code archived neural-networks artificial-life game-development research linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="openai/neural-mmo")