01 · Roasts
95% Jupyter, 0% Tests
Your language breakdown is 95% Jupyter Notebook and your test coverage is 0% across 9 of 10 repos. You've essentially built a very elaborate scratch pad and called it a portfolio.
soloPct: 100%
Every single repo is a solo project. You have 148 followers and totalPRsYear = 0. People are watching you commit to yourself in silence.
The 6-Year ANN
Your ANN repo spans 6 years and 25 commits. That's one commit every ~88 days. At this velocity, you'll finish a neural network sometime around 2041.
3-Day Project, Empty README
My-Agent-Lab was created and abandoned in 3 days with a README that literally says 'This project has no architecture selected.' Bold documentation strategy.
148 Followers, 0 PRs
You've somehow accumulated 148 followers without opening a single external PR or issue this year. They're following a ghost — a very productive, self-contained ghost.
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
- Impact25% weight56D
- Consistency20% weight65C
- Quality20% weight57D
- Depth15% weight58D
- Breadth10% weight55D
- Community10% weight50D
03 · Stats
365-day commit heatmap
346 active days
Language distribution
- Jupyter Notebook95%
- Python1%
- HTML1%
- CSS1%
- Java1%
- JavaScript0%
- Other1%
04 · Numbers
Owned repos
non-fork
90
Commits
last 12 months
465
Followers
148
Joined GitHub
May 2020
05 · Top repos
ShyamSundhar1411 /
Key-Hive-Kotlin
KeyHive is a local password manager mobile app in Kotlin with structured architecture (DI, repository pattern, paging), encryption utilities, and CSV import/export. No tests, no license, but typed + documented + CI configured for linting.
ShyamSundhar1411 /
structura-py
Structura is a Python CLI scaffolding tool with typed models (Pydantic), CI/lint automation, and multi-architecture support (MVC/MVCS/Hexagonal), but lacks unit tests and has minimal adoption (1 star). Quality is grounded in types, docs, and structured code; depth shown by multi-month activity with evolving features.
ShyamSundhar1411 /
Zenri-Express-Backend
Personal Express+TypeScript backend API for a life companion app with Prisma ORM, Supabase auth, and typed request validation. No README or CI/tests, but clean typed architecture with proper service-repository pattern and ~10k LOC scope.
ShyamSundhar1411 /
My-Go-Playground
Personal learning playground implementing 6+ rate-limiting algorithms and concurrency patterns in Go with tests and clear module structure, but no CI and zero adoption signals.
ShyamSundhar1411 /
Visionify-Backend
Educational FastAPI backend for image classification (MNIST/CIFAR-10) with clean architecture and DI patterns. Untyped Python, no tests, pre-commit configured. Early-stage project with 0 stars/forks suitable for learning but lacks production maturity.
ShyamSundhar1411 /
My-ML-Notebooks
Collection of ML learning notebooks (Jupyter + Python scripts) covering GPT implementation, computer vision, NLP, and LangGraph agents; typed Python code with structured modules but minimal documentation and no tests/CI.
ShyamSundhar1411 /
Zenri-Frontend
Young Next.js 15 + TypeScript frontend (883 KB) with 30 commits over ~3.5 months. Typed, has README, but minimal project-specific docs, no tests/CI, and appears to be a personal learning/experimental project with 0 stars/forks.
ShyamSundhar1411 /
My-Agent-Lab
Personal experimental FastAPI project for LangGraph-based agent systems with RAG/knowledge graph integration. Very early stage (3 days old, 6 commits), minimal documentation, no tests/CI, and no production-ready patterns.
ShyamSundhar1411 /
ANN
Early-stage personal neural network learning project in Jupyter Notebooks with no documentation, tests, CI, or license. 25 commits over ~6 years suggests occasional tinkering rather than sustained development.
ShyamSundhar1411 /
Unifyd-React-Native
Boilerplate Expo React Native starter project with zero commits in past month, no tests/CI, and generic scaffold README. Recently created (Jan 24, 2026) with minimal substantive code.
06 · Timeline
- May 13, 2020Joined GitHub
- Jun 15, 2020Created ANN — My first Neural Network
- Jul 29, 2022Created My-ML-Notebooks — Collection of Jupyter notebooks showcasing machine learning practices, including computer vision, NLP, classical ML algorithms, and paper replications.
- Oct 6, 2024Created Visionify-Backend — 🧠 Visionify is an interactive image classification platform. 🚀 This is its backend API built with FastAPI, clean architecture, and DI—supporting MNIST, Fashion MNIST, and CIFAR-1
- Dec 11, 2024Created Key-Hive-Kotlin — KeyHive is a cloud-free password manager designed to help you securely store, manage, and organize your passwords locally on your device
- Mar 7, 2025Created structura-py — Structura is a CLI tool that automates folder structure generation and dependency management for Python projects. It supports multiple architectures (MVC, MVCS, Hexagonal) and fram
- Sep 22, 2025Created Zenri-Express-Backend — Zenri Express Backend is an Express + TypeScript API server for Zenri, a personal life companion app. It provides type-safe database access with Prisma, request validation with Zod
- Nov 4, 2025Created Zenri-Frontend — Zenri Frontend - A modern Next.js 15 + TypeScript app for Zenri, a personal life companion platform. Built with shadcn/ui, Tailwind CSS, Zustand, and React Query, it features type-
- Jan 15, 2026Created My-Go-Playground — Hands-on implementations of core systems fundamentals and patterns in Go, built from first principles.
- Jan 24, 2026Created Unifyd-React-Native
- Feb 16, 2026Created My-Agent-Lab
- Apr 24, 2026Most recent push to Visionify-Backend
07 · Compare
08 · Rubric
How this score was produced
Overall = Σ (category × weight) + gentle top-end curve
Tier thresholds
▸ How the pipeline works
- 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.
- 02Triage.A small model reads every repo's file tree + README and picks the 20 files per repo that actually reveal how you code.
- 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.
- 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.
- 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.