Skip to content
CAI
Software that uses CAICheck a score

ManuXD32/AI-Doomsday-Toolbox

52.6

Adequate · 17 November 2026

512.7k

lines of production code

Kotlin

primary language

1

measurement over time

CAI band scale
CAI lens gauges

What this system is

Behavioural changes

1 commit (0 fixes) modifying asset\_upscaler

A change to existing behaviour in asset\_upscaler — 1 commit, 68 files: “Prepare GitHub release and public project update”.

_asset\upscaler · medium confidence · unverified

1 commit (0 fixes) modifying model-assets

A change to existing behaviour in model-assets — 1 commit, 5 files: “changes to in paint and enhancer using adetailers + converted models”.

model-assets · medium confidence · unverified

1 commit (0 fixes) modifying wear-protocol

A change to existing behaviour in wear-protocol — 1 commit, 2 files: “Rebuild Dev history without private files”.

wear-protocol · medium confidence · unverified

11 commits (2 fixes) modifying feature\_media\_i8mm, feature\_media\_snapdragon\_opencl

A change to existing behaviour in feature\_media\_i8mm, feature\_media\_snapdragon\_opencl — 11 commits (2 fixs), 7 files: “Fixed some chat llama native errors when handling the deepseek harness. Removed the pet simulated world. Fixed an issue with lingbot video generation. Updated binaries and in-app guide”; “Compacting context improvements + updated binaries”; “Rebuild Dev history without private files”; and 6 more.

_feature\_media\_i8mm, feature\_media\_snapdragon\opencl · medium confidence · unverified

15 commits (4 fixes) modifying feature\_llm\_snapdragon\_opencl

A change to existing behaviour in feature\_llm\_snapdragon\_opencl — 15 commits (4 fixs), 5 files: “Fixed some chat llama native errors when handling the deepseek harness. Removed the pet simulated world. Fixed an issue with lingbot video generation. Updated binaries and in-app guide”; “Compacting context improvements + updated binaries”; “Rebuild Dev history without private files”; and 10 more.

_feature\_llm\_snapdragon\opencl · medium confidence · unverified

2 commits (0 fixes) modifying gradle

A change to existing behaviour in gradle — 2 commits, 1 file: “Initial commit: AI Doomsday Toolbox v0.41”; “Update AI toolbox features and assets”.

gradle · medium confidence · unverified

37 commits (9 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 37 commits (9 fixs), 6 files: “Remove Delete folder from repository”; “Fixed some chat llama native errors when handling the deepseek harness. Removed the pet simulated world. Fixed an issue with lingbot video generation. Updated binaries and in-app guide”; “complete audit and OCR regression verification, fixed lint errors”; and 30 more.

(repo-wide) · low confidence · unverified

4 commits (1 fix) modifying wear

A change to existing behaviour in wear — 4 commits (1 fix), 28 files: “Merged complete rework of app's UI”; “Fixed some chat llama native errors when handling the deepseek harness. Removed the pet simulated world. Fixed an issue with lingbot video generation. Updated binaries and in-app guide”; “Rebuild Dev history without private files”; and 1 more.

wear · medium confidence · unverified

73 commits (30 fixes) modifying app/src

A change to existing behaviour in app/src — 73 commits (30 fixs), 4358 files: “Fixed error OCR ggufs not working”; “Added support for LORA on sdcpp and support for multiple servers on AI agent”; “SD model and model family detection improved”; and 68 more.

app/src · medium confidence · unverified

Fixes

6 commits (4 fixes) fixing asset\_debian

A fix in asset\_debian — 6 commits (4 fixs), 22 files: “Fixed some chat llama native errors when handling the deepseek harness. Removed the pet simulated world. Fixed an issue with lingbot video generation. Updated binaries and in-app guide”; “Easy chat mode + fixes for AI agent + improved pet simulation”; “Improved deepseek harness implementation, fully integrated with image generation through ADT and web search, synced projects created from the webUI and the app. Fixed a minor issue in image generation not being able to remove a selected image”; and 3 more.

_asset\debian · medium confidence · unverified

Dependencies

61 commits updating dependencies (25 manifests)

A dependency / build maintenance change in (dependencies) — 61 commits (24 fixs), 25 files: “Fixed error OCR ggufs not working”; “Added support for LORA on sdcpp and support for multiple servers on AI agent”; “SD model and model family detection improved”; and 56 more.

(dependencies) · medium confidence · unverified

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

Baseline

  • First survey — no prior run to compare against. CAI 52.6.

Lenses

  • Code Health 62.1
  • Architecture 91.2
  • Maturity 65.0
  • Readiness 47.8
  • Security 60.9
  • Domain Modelling 54.3
  • Accessibility 54.5
  • Performance 60.0

Changes since last survey

  • 100 commits — 70 feature/other, 30 fixes

By area

  • app/src — 71 commits
  • (root) — 12 commits
  • (repo) — 11 commits
  • .github/workflows — 2 commits
  • app/build.gradle.kts — 2 commits
  • feature_llm_armv9/src — 2 commits

Notable commits

  • fix: Added shimeji mode to the pet, changed farm style. fixed FGS error, fixed lingbot, wan errors when decoding video
  • fix: Added support for Stable diffusion distributed inference, fixed model downloading stale downloads and half downloaded files taking up space. Added initial experimental support for GPU acceleration in llamacpp and sdcpp. Added backend, backend params and max VRAM to sdcpp UIs to allow sequantial loading of the models. Tried to fix issue can't enable GNU RELRO protection
  • fix: Added support for voice clonning and TTS through llamacpp and audio and music generation with LiteRT, fixed repo navigation bug
  • fix: Cleaning code, fixed codeql
  • fix: Easy chat mode + fixes for AI agent + improved pet simulation
  • fix: Final fixes for the release
  • fix: Final redesign. Fixed some issues in chat llama native delegating work to the harness and passing files from the main chat
  • fix: Fix for Qwen Image + Minor deepseek ai agent fixes
  • fix: Fix for multiple runtimes not showing ADT models correctly
  • fix: Fix to AI agents implementation plan buttons not working
  • fix: Fixed app building up trash and getting laggy, specially after heavy AI usage, Added in-paint to manga/comic translation to avoid complete OCR. Fixed auto detection of sdcpp model types
  • fix: Fixed aproval button error in AI Agent, added calculation of actual context budget when using parallel >1
  • fix: Fixed audio gen bugs and model type override by users
  • fix: Fixed audio generation error and minor bugs in the download queue
  • fix: Fixed error OCR ggufs not working
  • fix: Fixed error on the finish task tool in AI Agent
  • fix: Fixed error with VAD 5.1.2 download, added a curated list of bundles to download for using sdcpp
  • fix: Fixed max context error where the harness allowed prompts bigger than max ctx
  • fix: Fixed some chat llama native errors when handling the deepseek harness. Removed the pet simulated world. Fixed an issue with lingbot video generation. Updated binaries and in-app guide
  • fix: Fixed upscale compose error, fixed PDF intake
  • …and 80 more

Architecture

  • 0 containers · 3 bounded contexts · 3 dependency edges (baseline)

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

ManuXD32/AI-Doomsday-Toolbox was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 17 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit 007c5237e94f387b5f0f39e325b2c5aa01efee23 — the exact code this score is about.
  • Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
  • Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.85+preprod-eba6548ac50f.