01 · Roasts
CI unicorn
CI-CD has Jest and GitHub Actions; most of the remaining portfolio appears to have missed the same invitation.
Notebook gravity
85% Jupyter Notebook makes the account look ML-heavy, while packaging and reproducibility are still mostly optional side quests.
Zero-star startup
Six-plus named projects are shipping, but 0 stars, 0 forks, and 0 followers mean the audience has not arrived yet.
Prototype parade
CodeGuardian-AI, Meetmind, and Attendai-app show real ambition; tests, READMEs, and CI keep getting cut before release.
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% weight55D
- Breadth10% weight55D
- Community10% weight25F
03 · Stats
365-day commit heatmap
34 active days
Language distribution
- Jupyter Notebook85%
- JavaScript7%
- HTML4%
- Python1%
- CSS1%
- Java1%
- Other1%
04 · Numbers
Owned repos
non-fork
20
Commits
last 12 months
96
Followers
0
Joined GitHub
Apr 2024
05 · Top repos
KalyanSai956 /
CI-CD
Small Express CI/CD practice service with two endpoints, a reusable sum module, Jest tests, and GitHub Actions automation, but no demonstrated adoption or substantial documentation.
KalyanSai956 /
LeetCode
A small Java LeetCode solution collection with roughly 30 commits and several correct algorithm implementations, but no documentation, tests, CI, license, or evidence of external adoption.
KalyanSai956 /
Attendai-app
A non-trivial Streamlit attendance app with face and voice recognition, Supabase persistence, teacher/student workflows, and subject enrollment, but no documentation, tests, CI, license, or typed implementation.
KalyanSai956 /
KalyanSai956
A polished GitHub profile README showcasing four named AI/software projects and a portfolio link, but the repository itself contains no implementation, tests, CI, license, or typed source.
KalyanSai956 /
My_Portfolio
A functional React/Vite portfolio with routed home and projects pages, themed UI, Supabase visitor counting, and links to four showcased projects, but no tests, CI, license, or project documentation.
KalyanSai956 /
CodeGuardian-AI
CodeGuardian-AI is a structured but early-stage multi-service prototype combining React, Express, FastAPI, LangGraph, embeddings, and Qdrant for repository analysis, with no documented adoption or validation artifacts.
KalyanSai956 /
Meetmind
MeetMind is an early meeting-intelligence scaffold with a minimal FastAPI health service, Express/MongoDB backend bootstrap, and largely unmodified Vite React starter UI.
KalyanSai956 /
AIML
A broad but lightly packaged AIML notebook collection spanning supervised learning, deep learning, NLP, reinforcement learning, clustering, and API data collection; it has no documented product, adoption signals, tests, CI, license, or typed implementation.
KalyanSai956 /
Attend-ai-landing-page
A small Flask-served Attend AI marketing page with a polished responsive HTML/CSS presentation, six teacher workflow steps, three feature cards, and links to an external Streamlit app, but no tests, CI, documentation, or license.
KalyanSai956 /
Agentic_AI
A tiny, one-commit Python experiment containing three direct Agno examples for cooking assistance, persistent memories, and multi-agent teamwork, with no documentation, tests, CI, or license.
KalyanSai956 /
SmartHire_ATS
SmartHire_ATS is currently an empty one-commit scaffold: only a minimal README is present, with no implementation, tests, CI, license, or repository configuration.
KalyanSai956 /
TaskFlow
TaskFlow is an empty repository with zero stars, zero forks, no commits in the sample, and no fetched source files or project artifacts.
06 · Timeline
- Apr 2, 2024Joined GitHub
- Jul 4, 2026Created SmartHire_ATS — Smart applicant tracking system that helps recruiters manage candidates, job applications, and hiring workflows.
- Jul 10, 2026Created Attendai-app — AI-powered attendance management application for tracking, managing, and analyzing attendance efficiently.
- Jul 10, 2026Created Attend-ai-landing-page — AI-powered attendance platform landing page designed to showcase smart, automated attendance management.
- Jul 17, 2026Created KalyanSai956
- Jul 21, 2026Created My_Portfolio — Personal developer portfolio showcasing projects, technical skills, experience, and software development work.
- Aug 6, 2026Created LeetCode
- Aug 10, 2026Created Agentic_AI
- Aug 13, 2026Created CI-CD
- Aug 14, 2026Created Meetmind — AI meeting intelligence platform that transforms conversations into summaries, decisions, and actionable tasks.
- Aug 15, 2026Created AIML
- Aug 31, 2026Created TaskFlow
- Aug 31, 2026Created CodeGuardian-AI
- Sep 5, 2026Most recent push to Attendai-app
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.