# Equim-chan/Mortal

🚀🀄️ A fast and strong AI for riichi mahjong, powered by Rust and deep reinforcement learning.

Repository: https://github.com/Equim-chan/Mortal
Canonical: https://ross.abutalabs.com/products/mortal
Homepage: https://mortal.ekyu.moe
Language: Rust
License: AGPL-3.0
License Family: copyleft
Topics: ai, deep-learning, game-ai, mahjong, reinforcement-learning, riichi, mjai, mahjong-ai
Last push: 2025-09-28T14:29:24+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 44, release rhythm 35, longevity 100
- inputs: {"age_days": 1867, "days_push": 339, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1527, forks 218 (observed 2026-08-28T04:04:58.509207+00:00)

## What it is
Mortal is a free and open-source AI for Japanese (riichi) mahjong powered by deep reinforcement learning, written in Rust with a Python interface. It includes a fast mahjong emulator (libriichi), an mjai-compatible interface, and serves as the backend for mjai-reviewer.

## Use cases
- build a riichi mahjong AI bot
- review my Tenhou mahjong games
- simulate mahjong games at high speed for RL training
- train a deep reinforcement learning agent for mahjong
- analyze mahjong discards and decisions
- integrate an mjai-compatible mahjong engine

## When to choose
- you need a strong, open-source riichi mahjong AI
- you want a fast Rust-based mahjong emulator for self-play training
- you want mjai-compatible tooling or a review backend

## When to avoid
- you need other mahjong variants like Chinese or American mahjong
- you need pre-trained model weights without reading the author's release policy
- you need a plug-and-play GUI client rather than a library/backend

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, reinforcement-learning, game-engine, simulation, sdk
- domain: artificial-intelligence, reinforcement-learning, gaming-tools
- platform: rust, python, cross-platform
- tags: riichi-mahjong, mahjong-ai, mjai, game-ai, deep-reinforcement-learning, tenhou, libriichi, game-development, gpu

## Member repositories
- Equim-chan/Mortal (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:58.509207+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 2026-08-30T04:31:32.326213+00:00, confidence not recorded.
  - readme: https://github.com/Equim-chan/Mortal (fetched 2026-08-28T04:04:58.509207+00:00, sha ceef7b355fb2)
  - homepage: https://mortal.ekyu.moe (fetched 2026-08-29T11:33:59.384720+00:00, sha b5f40a44de83)
- Data as of 2026-08-30T08:39:29.467469+00:00.