# microsoft/malmo

Project Malmo is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. We aim to inspire a new generation of research into challenging new problems presented by this unique environment. --- For installation instructions, scroll down to *Getting Started* below, or visit the project page for more information:

Repository: https://github.com/microsoft/malmo
Canonical: https://ross.abutalabs.com/products/malmo
Homepage: https://www.microsoft.com/en-us/research/project/project-malmo/
Language: Java
License: MIT
License Family: permissive
Archived: true
Last push: 2025-09-03T13:10:21+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 40, release rhythm 8, longevity 100
- inputs: {"age_days": 3760, "days_push": 364, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4270, forks 608 (observed 2026-08-28T04:08:40.885598+00:00)

## What it is
Project Malmo is a platform for artificial intelligence experimentation and research built on top of Minecraft, providing a gym-like environment (MalmoEnv) for training agents. It supports multi-agent missions and can be installed as a native Python wheel or pre-built binaries.

## Use cases
- train reinforcement learning agents in Minecraft
- run AI experiments in a 3D game environment
- set up a gym environment for Minecraft research
- coordinate multi-agent missions in Minecraft
- teach AI and machine learning with a game sandbox
- benchmark learning algorithms on challenging 3D tasks

## When to choose
- you need a rich 3D sandbox for reinforcement learning research
- you want a gym-compatible Minecraft environment without native code
- you need multi-agent experimentation in a game world

## When to avoid
- you need a lightweight or fast 2D RL environment
- you require the legacy Malmo examples with the newer MalmoEnv API
- you are not willing to manage a Minecraft/Java setup

## Facets
- artifact type: framework
- maturity: maintenance
- function: machine-learning, reinforcement-learning, simulation, game-engine, sdk
- domain: artificial-intelligence, machine-learning, reinforcement-learning
- platform: python, jvm, cross-platform, windows
- tags: minecraft, gym-environment, ai-research, marlo, multi-agent, microsoft-research, game-development, research, linux, macos

## Member repositories
- microsoft/malmo (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:40.885598+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 2026-08-29T18:22:01.787103+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/malmo (fetched 2026-08-28T04:08:40.885598+00:00, sha 05a3f7422242)
  - homepage: https://www.microsoft.com/en-us/research/project/project-malmo/ (fetched 2026-08-29T09:11:44.504374+00:00, sha a4b4310bbb8d)
  - site_page: https://www.microsoft.com/en-us/research/about-microsoft-research (fetched 2026-08-29T09:11:44.506775+00:00, sha 662089aedfa3)
  - site_page: https://learn.microsoft.com/docs (fetched 2026-08-29T09:11:44.508589+00:00, sha f29800be2b9a)
  - site_page: https://www.microsoft.com/about (fetched 2026-08-29T09:11:44.513337+00:00, sha a516731f0fea)
  - site_page: https://www.microsoft.com/en-us/research/project/project-malmo/news-and-awards (fetched 2026-08-29T09:11:44.510178+00:00, sha d4e78f37c40b)
- Data as of 2026-08-30T08:39:29.467469+00:00.