# Equim-chan/mjai-reviewer

🔍🀄️ Review mahjong game log with mjai-compatible mahjong AI.

Repository: https://github.com/Equim-chan/mjai-reviewer
Canonical: https://ross.abutalabs.com/products/mjai-reviewer
Homepage: https://mjai.ekyu.moe
Language: Rust
License: Apache-2.0
License Family: permissive
Topics: mahjong, riichi, tenhou, mahjongsoul, jantama, mahjong-ai
Last push: 2025-02-22T07:35:31+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 8, release rhythm 8, longevity 100
- inputs: {"age_days": 2378, "days_push": 557, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1233, forks 140 (observed 2026-08-28T04:04:04.549856+00:00)

## What it is
A Rust CLI tool that reviews riichi mahjong game logs using mjai-compatible AI engines such as Mortal and akochan. It fetches logs from Tenhou, Mahjong Soul, Riichi City, and Hime Mahjong (or local tenhou.net/6 JSON files) and produces a detailed review of each decision.

## Use cases
- review my tenhou game log with mortal
- analyze mahjong soul game for mistakes
- find wwyd mistakes in riichi mahjong games
- review a local tenhou.net/6  log file
- compare my play against akochan AI
- review only specific kyoku of a mahjong game

## When to choose
- you play riichi mahjong on Tenhou, Mahjong Soul, Riichi City, or Hime Mahjong and want AI-powered game reviews
- you want a free, local, scriptable alternative to the web app
- you want to choose between Mortal and akochan engines or specific Mortal networks

## When to avoid
- you only play non-standard rules or three-player games
- you want a no-install experience and should use the hosted web app instead
- you need reviews for games outside the supported platforms

## Facets
- artifact type: cli-tool
- maturity: active
- function: developer-tools, cli, machine-learning
- domain: gaming-tools, developer-tools, machine-learning
- platform: windows, cli
- tags: mahjong, riichi, tenhou, mahjongsoul, mjai, game-log-review, mortal, akochan, linux, macos, web-server

## Member repositories
- Equim-chan/mjai-reviewer (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:04.549856+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 2026-08-30T08:22:13.191323+00:00, confidence not recorded.
  - readme: https://github.com/Equim-chan/mjai-reviewer (fetched 2026-08-28T04:04:04.549856+00:00, sha 907272aefa64)
  - homepage: https://mjai.ekyu.moe (fetched 2026-08-29T12:21:41.838287+00:00, sha 9daf7fc9e948)
- Data as of 2026-08-30T08:39:29.467469+00:00.