▸ This tool was built by an AI agent from Zoral
← RATE MY GITHUB

#171 — Top 88.9%

Yudhyy

McCodey – e/alt

C

Getting there

Overall

0.0

/ 100

01 · Roasts

Notebook monoculture

95% Jupyter Notebook means the GPU is going brrr, but the language portfolio is mostly one long cell execution.

CI wanted

Klaudia proves you can wire CircleCI; tunnel-engine, klaudia-core, and mcp-gsheets are still waiting for the invite.

Shipyard, not user base

146 public repos and 68 total stars: the release cadence is louder than the adoption evidence.

Tested islands

Tachikoma-Observatory's 101 tests and docx-compressor's end-to-end suite make the untested MCP repos look especially exposed.

Built using

Zoral

Shadows one worker for a week, then takes over their job with zero extra setup. Behaves exactly like the original.

zoral.ai

02 · Category breakdown

  • Impact
    25% weight
    62C
  • Consistency
    20% weight
    65C
  • Quality
    20% weight
    69C
  • Depth
    15% weight
    58D
  • Breadth
    10% weight
    55D
  • Community
    10% weight
    55D

03 · Stats

365-day commit heatmap

88 active days

Less
More

Language distribution

7 langs
  • Jupyter Notebook95%
  • Python4%
  • TypeScript0%
  • HTML0%
  • Jinja0%
  • Shell0%
  • Other1%

04 · Numbers

Owned repos

non-fork

56

Commits

last 12 months

479

Followers

23

Joined GitHub

Dec 2022

05 · Top repos

Yudhyy /

Klaudia

60/100

Klaudia is a substantial self-hosted AI accounting system with FastAPI, LangGraph/MCP agents, PostgreSQL-backed ledgers, OCR ingestion, deterministic numeric verification, approval gates, and automated CI tests, but has only 7 stars and no license.

I25Q72D50
READMETestsCI
Python77d ago

Yudhyy /

Tachikoma-Observatory

50/100

A documented Python benchmark dashboard with a 15-scenario deterministic tool-calling suite, lockstep multi-model execution, SQLite history, and 101-test coverage; adoption remains limited at 2 stars.

I25Q60D50
READMETests
Python21mo ago

Yudhyy /

tunnel-engine

48/100

A substantial, documented Python LLM gateway with vLLM, LMCache, LiteLLM routing, guardrails, observability, orchestration, and broad unit coverage, but only 4 stars and no demonstrated external adoption.

I25Q55D50
READMETests
Python41mo ago

Yudhyy /

docx-compressor

45/100

A focused, locally-run DOCX image compressor with a polished README, modular src layout, and meaningful end-to-end tests, but only 2 stars and a short one-week development burst limit demonstrated adoption and longevity.

I25Q68D20
READMETests
Python21mo ago

Yudhyy /

klaudia-dev

42/100

A typed Expo/React Native ledger-chat app with authentication, SSE streaming, attachment handling, and approval workflows; it has focused service tests but no visible adoption, README, CI, or license.

I20Q55D50
TestsTyped
TypeScript0this week

Yudhyy /

mcp-gsheets

39/100

A documented, modular Python MCP server exposing 16 Google Sheets read, write, and sheet-management tools, but with no demonstrated adoption, tests, CI, or license.

I22Q45D50
README
Python02mo ago

Yudhyy /

klaudia-core

38/100

A structured Python/LangGraph supervisor with provider abstraction, MCP integration, and careful sheet-coordinate safeguards, but currently has 0 stars, minimal README documentation, no tests or CI, no license, and no static typing.

I20Q45D50
README
Python01mo ago

Yudhyy /

mcp-sqlite

33/100

Small, undocumented-in-practice MCP SQLite server exposing asynchronous CRUD tools over FastMCP; modular Python layout is offset by absent tests, CI, license, and meaningful setup documentation.

I20Q45D35
README
Python01mo ago

Yudhyy /

pytorch-protocol

28/100

A same-day PyTorch learning notebook centered on one marimo file, with clear setup notes but no tests, CI, license, or demonstrated external adoption.

I15Q35D35
README
Python010d ago

Yudhyy /

Yudhyy

23/100

A lightly adopted GitHub profile repository with 1 star and a README describing LLM/agentic-AI interests, but no fetched source files or evidence of a packaged, tested product.

I20Q20D35
README
Unknown1this week

Yudhyy /

relicbench

12/100

Relicbench is a newly created, zero-star benchmarking concept with an evocative README but no sampled implementation, tests, CI, license, or typed-language evidence.

I15Q20D5
README
Unknown02mo ago

Yudhyy /

TensorTonic-Solutions

8/100

TensorTonic-Solutions is a newly created, one-commit personal solutions repository with a README describing synchronization from TensorTonic but no fetched source files or implemented solutions yet.

I10Q10D5
README
Unknown01mo ago

06 · Timeline

  1. Dec 2, 2022
    Joined GitHub
  2. Sep 28, 2023
    Created Yudhyy
  3. Jan 13, 2026
    Created mcp-gsheets
  4. Apr 16, 2026
    Created klaudia-core
  5. Apr 16, 2026
    Created mcp-sqlite
  6. Apr 16, 2026
    Created Klaudia — Self-hosted AI accountant. Reads receipts / invoices, reconciles ledgers, checks its own numbers, and asks before anything irreversible. Open source, agentic, runs on your infrastr
  7. Apr 19, 2026
    Created klaudia-dev
  8. Jun 1, 2026
    Created Tachikoma-Observatory — A lightweight evaluation framework for testing Small Language Models (SLMs) on precise tool-calling capabilities to ensure they are production-ready.
  9. Jun 12, 2026
    Created relicbench — The last sanctuary of machine intelligence.
  10. Jun 12, 2026
    Created tunnel-engine — A production-grade LLM infra engine that uses vLLM for fast inference, LMCache for smart context caching, and LiteLM to handle multi-model routing and load balancing.
  11. Jul 20, 2026
    Created docx-compressor — Your private DOCX compression tool
  12. Jul 23, 2026
    Created TensorTonic-Solutions — My solutions to TensorTonic problems
  13. Aug 25, 2026
    Created pytorch-protocol — pytorch stuff
  14. Sep 3, 2026
    Most recent push to Yudhyy

07 · Compare

github.com/
Yudhyy · 6dmedian coder

08 · Rubric

How this score was produced

Overall = Σ (category × weight) + gentle top-end curve

CategoryWeightScoreContrib.
Raw total62.0
Top-end curve+5.3
Final overall67.3

Tier thresholds

S90100Mass-producing humansA8089Ship machineB7079Solid engineerC6069Getting thereD4059README enthusiastF039GitHub tourist
▸ How the pipeline works
  1. 01Scrape.Pull every non-fork repo pushed in the last 90 days, plus your contribution calendar, followers, and language byte counts — straight from GitHub's REST & GraphQL APIs.
  2. 02Triage.A small model reads every repo's file tree + README and picks the 20 files per repo that actually reveal how you code.
  3. 03Grade each repo. All repos run in parallel through a fast scoring model that reads the picked files and rates each one independently on Impact, Quality, and Depth — with evidence citations.
  4. 04Aggregate. A larger reasoning model combines the per-repo scores with server-computed stats (heatmap, commit cadence, language entropy, follower count) to produce the 6-dimension profile score + roasts.
  5. 05Correct.Deterministic server-side checks enforce anchor-scale floors (e.g. a profile with 2,000+ public commits can't score 30 Consistency) and recompute the final verdict.

~90 seconds per profile, ~$0.25 in compute. Total of ~240 files read across your top-12 repos. One rating per GitHub account per day.

▸ Data sources & caveats
  • Heatmap & commit totals: GitHub GraphQL contributionsCollection — covers the last 365 days, includes private repos when the user has opted in (default).
  • Language %: byte totals across the top 30 owned non-fork repos.
  • Curve: a small upward nudge centered on raw score ≈ 70, capping at 100. Prevents specialists from being unfairly penalised for narrow breadth.
  • Anchor corrections: when server-measured signals (e.g. privateWorkLikely, multiRepoVolume, follower count) mandate a minimum category score, the aggregation step enforces it. These are signal-conditional, not identity-based floors.
Yudhyy · 67.3/100 — Rate My GitHub