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

#637 — Top 63.9%

Anirudh2627

D V Anirudh

D

README enthusiast

Overall

0.0

/ 100

01 · Roasts

Portfolio, not pull requests

Seven named projects are shipping, yet the account has 0 stars, 0 forks, and only 4 followers.

CI has not been invited

All seven scored repositories lack both tests and CI, including finpilot-ai and LLM-Sandbox.

Notebook gravity

Jupyter Notebook accounts for 88% of the language mix; the ML work needs more packaged, reproducible surfaces.

Key to nowhere

ai-traffic-police includes a hard-coded Roboflow API key, turning a CV demo into a credential-hygiene lesson.

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
    56D
  • Consistency
    20% weight
    55D
  • Quality
    20% weight
    55D
  • Depth
    15% weight
    50D
  • Breadth
    10% weight
    55D
  • Community
    10% weight
    25F

03 · Stats

365-day commit heatmap

26 active days

Less
More

Language distribution

6 langs
  • Jupyter Notebook88%
  • HTML4%
  • Python4%
  • TypeScript3%
  • JavaScript1%
  • CSS0%

04 · Numbers

Owned repos

non-fork

12

Commits

last 12 months

79

Followers

4

Joined GitHub

Jul 2025

05 · Top repos

Anirudh2627 /

finpilot-ai

42/100

A substantial typed React/FastAPI financial assistant with portfolio APIs, market lookup, ML/SHAP/LIME modules, and a polished explainability dashboard, but currently has no adoption signals, tests, CI, or license and includes substantial demo/static behavior.

I25Q58D35
READMETyped
TypeScript★ 02mo ago

Anirudh2627 /

LLM-Sandbox

35/100

A documented FastAPI security sandbox with layered prompt filtering, encoded-secret guardrails, Redis caching, rate limiting, Docker deployment, and a concise multi-module Python layout, but no tests, CI, license, or typed annotations.

I20Q50D35
README
Python★ 02mo ago

Anirudh2627 /

CNN-built-from-scratch

34/100

A documented MNIST learning project implementing convolution, pooling, activations, and an MLP in a Jupyter notebook with NumPy, but it has no visible tests, CI, license, or external adoption.

I22Q40D35
README
Jupyter Notebook★ 04mo ago

Anirudh2627 /

TrustLens-NLP

33/100

A documented Flask NLP demo with a polished HTML interface, handcrafted review features, and an ensemble model, but no visible adoption, tests, CI, license, or typed implementation.

I22Q40D35
README
HTML★ 04mo ago

Anirudh2627 /

ai-traffic-police

29/100

Documented computer-vision notebook project covering CNN vehicle classification, YOLOv8 counting, traffic violations, and emergency vehicles, with concrete training runs but limited reproducibility and no production packaging.

I20Q38D20
README
Jupyter Notebook★ 02mo ago

Anirudh2627 /

dynamic-site

28/100

A functional Express/Mongoose student-record dashboard with CRUD, search, and summary metrics, but it has no README, tests, CI, license, or typed code and shows no external adoption.

I20Q30D35
JavaScript★ 03mo ago

Anirudh2627 /

Fake-News-Detector-NLP-Classification

17/100

A small FastAPI misinformation-classification endpoint that loads serialized model artifacts and exposes /predict, but has no documented, tested, licensed, or CI-supported project surface.

I20Q25D5
Python★ 04mo ago

06 · Timeline

  1. Jul 17, 2025
    Joined GitHub
  2. Feb 16, 2026
    Created TrustLens-NLP — TrustLens NLP is a full-stack Natural Language Processing web application that detects whether a product review is FAKE or GENUINE using advanced machine learning and linguistic
  3. Feb 21, 2026
    Created CNN-built-from-scratch — Built a CNN from scratch
  4. Feb 22, 2026
    Created Fake-News-Detector-NLP-Classification — Detecting misinformation using Machine Learning and Natural Language Processing.
  5. Jul 17, 2026
    Created finpilot-ai
  6. Jul 23, 2026
    Created dynamic-site
  7. Aug 19, 2026
    Created ai-traffic-police
  8. Aug 27, 2026
    Created LLM-Sandbox
  9. Sep 5, 2026
    Most recent push to finpilot-ai

07 · Compare

github.com/
Anirudh2627 · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total51.5
Top-end curve+3.0
Final overall54.5

Tier thresholds

S90–100Mass-producing humansA80–89Ship machineB70–79Solid engineerC60–69Getting thereD40–59README enthusiastF0–39GitHub 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.
Anirudh2627 · 54.5/100 — Rate My GitHub