01 · Roasts
The 30-Minute Architect
AI-Workforce-OS has a Supervisor agent, Travel agent, Hotel agent, Finance agent, HR agent... and exactly 2 commits spanning 30 minutes. That's less time than it takes to read the architecture you designed.
Sprint Addiction
patch2_training: 1 day. Football_tracking_system: 3 days. inaippuai-cards: 2 days. Facielis: 1 commit. You're not building software, you're dropping concept grenades and walking away.
CI? Never Heard of Her
10 repos scored, 0 have CI. You've got Whisper ASR, ChromaDB RAG, ONNX embeddings, and Mask R-CNN — but automating `pytest` in a GitHub Action is apparently too much to ask.
LICENSE.md is 3 Lines, Gokul
Not a single repo in your portfolio has a license file. You've written medical AI disclaimers in agent.py but haven't told anyone if they're legally allowed to run your code.
93% Solo Artist
602 commits this year, 2 PRs, 0 issues filed — soloPct of 93%. You're building an entire AI ecosystem in isolation. Open source is a conversation, not a monologue.
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% weight62C
- Consistency20% weight65C
- Quality20% weight57D
- Depth15% weight58D
- Breadth10% weight80A
- Community10% weight55D
03 · Stats
365-day commit heatmap
173 active days
Language distribution
- JavaScript51%
- Python18%
- TypeScript11%
- HTML10%
- Dart7%
- CSS1%
- Other2%
04 · Numbers
Owned repos
non-fork
74
Commits
last 12 months
602
Followers
20
Joined GitHub
Dec 2024
05 · Top repos
Gokul-bit165 /
AI-Voice-Hospital-Consultation-System
Voice-first hospital consultation prototype with FastAPI backend, Next.js frontend, Whisper ASR, ChromaDB RAG, and medical LLM agent. Multi-month development with 3MB codebase and structured architecture, but experimental scope with no production deployment.
Gokul-bit165 /
patch2_training
Personal research project implementing Mask R-CNN for drone waterway instance segmentation with 6 custom classes. Typed Python codebase with structured scripts, comprehensive documentation, and training/evaluation pipeline but no tests, CI, or production adoption signals.
Gokul-bit165 /
nenAI
NENAI is an ambitious offline Flutter AI memory engine with clean architecture, ONNX embeddings, Gemma LLM integration, and multi-agent context reasoning. Well-documented (README + 4 design docs) and typed. Tests exist but no CI. Zero external adoption yet; experimental phase.
Gokul-bit165 /
modern-information-retrieval
Medicinal plant IR benchmark implementing BM25, dense vector search (FAISS), and hybrid RRF fusion. Features comprehensive evaluation suite (15 frozen queries, 47-doc corpus), research-grade documentation, type hints, and pytest tests. Created 2 days ago with 7 commits, small experiment scope.
Gokul-bit165 /
Football_tracking_system
Early-stage computer vision football tracking system with YOLO, ByteTrack, and pitch homography. Typed Python codebase with meaningful README and structured modules, but incomplete core implementation, no tests/CI, and no external adoption.
Gokul-bit165 /
portfolio
Personal portfolio project with 26 commits over ~12 days. JavaScript with tests and alternate documentation (docs/, design.md, ARCHITECTURE.md, STATUS.md), but no CI, license, or gitignore. Typed language absent, README minimal.
Gokul-bit165 /
Facielis
Early-stage SaaS platform for facility inspection with typed Next.js backend, rule engine, and full Prisma schema. Single recent commit; experimental, pre-launch pilot project for BIT-Sathy.
Gokul-bit165 /
inaippuai-cards
Early-stage React/Vite SPA for public digital business cards with glassmorphic UI, analytics, and QR codes. Typed code, structured layout, and meaningful docs, but very new (2 days old), minimal commits (4 of 30), no tests/CI, and experimental backend integration.
Gokul-bit165 /
AI-Workforce-OS
Ambitious multi-agent workflow orchestration platform (FastAPI + SQLAlchemy) with hierarchical agents, event bus, and WebSocket streaming. Launched 2026-07-16 with 2 commits over 30 minutes; demonstrates sophisticated architecture but lacks tests, CI, README, license, type safety, and meaningful documentation.
Gokul-bit165 /
Gokul-bit165
Personal GitHub profile README showcasing skills and achievements with no actual project code—a portfolio landing page rather than a functional software project.
06 · Timeline
- Dec 15, 2024Joined GitHub
- Sep 10, 2025Created Gokul-bit165
- Jul 8, 2026Created inaippuai-cards
- Jul 13, 2026Created AI-Voice-Hospital-Consultation-System
- Jul 16, 2026Created AI-Workforce-OS
- Jul 17, 2026Created Football_tracking_system
- Jul 19, 2026Created portfolio
- Jul 20, 2026Created modern-information-retrieval — A practical implementation of modern Information Retrieval (IR) techniques, featuring BM25, dense vector search, Hybrid Search with Reciprocal Rank Fusion (RRF), and comprehensive
- Jul 29, 2026Created patch2_training
- Aug 1, 2026Created Facielis — Facility Assurance Platform
- Aug 4, 2026Created nenAI
- Aug 19, 2026Most recent push to Gokul-bit165
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.