01 · Roasts
CI allergy
Eleven scored repos, and CI is absent from every one. The build pipeline is currently a belief system.
Starving portfolio
Flowio, Zentra, ContractAI, and the chat app ship serious feature lists, yet the account totals only 9 stars.
Test rationing
Only ContractAI and the Express template show tests; the RAG and SaaS projects are running mostly on optimism.
Horizontal grinder
183 sampled commits across repos says you build constantly; 432 yearly commits make the empty heatmap weeks look like strategic silence.
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% weight63C
- Consistency20% weight65C
- Quality20% weight57D
- Depth15% weight58D
- Breadth10% weight65C
- Community10% weight25F
03 · Stats
365-day commit heatmap
72 active days
Language distribution
- JavaScript63%
- TypeScript23%
- Python11%
- CSS1%
- C++1%
- HTML0%
- Other1%
04 · Numbers
Owned repos
non-fork
83
Commits
last 12 months
432
Followers
6
Joined GitHub
May 2022
05 · Top repos
Sayanduary /
Flowio-Project-Management-FullStackApp
Flowio is a named, deployed project-management SaaS with Clerk-authenticated workspaces, Prisma/PostgreSQL data modeling, task views, analytics, comments, and Inngest email workflows, but it lacks tests, CI, licensing, and typed code.
Sayanduary /
gdrive-rag-system
Zentra is a substantial full-stack Google Drive RAG application with FastAPI, React, PostgreSQL/pgvector, embeddings, OCR, OAuth, streaming chat, and background ingestion, but it has no demonstrated adoption or automated validation.
Sayanduary /
sayanduary-portfolio
A polished React/Vite portfolio site presenting five named projects, interactive theme/navigation/contact features, and substantial component styling, but with 0 stars, no external-adoption evidence, no tests or CI, and no project documentation.
Sayanduary /
CodeMind-Fullstack-ai-agent
Typed Next.js chat UI scaffold with substantial reusable AI-element components, but core chat submission is still console-only and the repository lacks tests, CI, license, and product documentation.
Sayanduary /
chat-app-fullstack-socket_io
A documented JavaScript React/Express chat application with MongoDB, JWT auth, Socket.io typing and WebRTC signaling, plus image uploads and email integration; it has meaningful feature scope but no tests, CI, license, or adoption signals.
Sayanduary /
mernstack-c-node-template
A small TypeScript Express starter with basic logging, error handling, and two Jest tests; it is structured and typed but has no documented product, adoption signals, CI, or license.
Sayanduary /
google-calender-agent-v2
Typed Bun/TypeScript calendar agent with LangGraph tool orchestration, Google OAuth, event CRUD, and a terminal UI; documented by README and plan.md but lacks tests, CI, and a license.
Sayanduary /
ai-contract-management
A documented JavaScript contract-management MVP with PDF ingestion, pgvector RAG, LangGraph Q&A, AI risk analysis, reminders, and React workflows, but no visible adoption, CI, license, or production hardening.
Sayanduary /
Sayanduary
A GitHub profile-style repository centered on a richly formatted README, with no sampled source files, tests, CI, license, or demonstrated external adoption.
Sayanduary /
go-start
A small Go learning repository containing numbered examples for functions, closures, pointers, structs, interfaces, enums, and generics, but no documented product, tests, CI, or adoption signals.
Sayanduary /
ping-panda
A very early Next.js/TypeScript scaffold with Prisma and Tailwind utility setup, but only two sampled commits, no product-specific README content, sparse page sections, and an incomplete MaxWidthWrapper implementation.
06 · Timeline
- May 4, 2022Joined GitHub
- Nov 22, 2023Created Sayanduary
- Feb 26, 2025Created sayanduary-portfolio
- Jul 4, 2026Created ping-panda
- Jul 4, 2026Created chat-app-fullstack-socket_io
- Jul 24, 2026Created mernstack-c-node-template
- Aug 3, 2026Created go-start
- Aug 16, 2026Created gdrive-rag-system
- Aug 25, 2026Created google-calender-agent-v2
- Sep 1, 2026Created CodeMind-Fullstack-ai-agent
- Sep 2, 2026Created Flowio-Project-Management-FullStackApp
- Sep 3, 2026Created ai-contract-management
- Sep 3, 2026Most recent push to Flowio-Project-Management-FullStackApp
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.