01 · Roasts
Sprint King, Sustain Stranger
Aurora-Risk-Architecture has 16 commits... all within a 3-minute window on 2026-03-13. Appscrip dropped everything in a single day. AURORA was created and last pushed within 60 seconds of each other. You're not building — you're speed-running repo creation.
94% Notebooks, 0% Shame
Your langPcts show Jupyter Notebook at 94%. That's not a language distribution, that's a confession. You have Go and TypeScript repos — yet the byte-count is dominated by .ipynb checkpoints and markdown cells.
The Naming Illusion
Repos named 'VIDE-AI-ENABLED-VIDEO-AND-IMAGE-EDITOR' and 'Autonomous-Multi-Agent-AI-Organization' suggest galaxy-brain ambition. One has 2KB and 2 commits. The other is 7 weeks old. The longer the name, the shorter the commit history.
339 Followers, 52 Stars
You've accumulated 339 followers — a respectable social signal — but your 56 public repos have only pulled 52 total stars combined. That's less than 1 star per repo on average. Your follower-to-star ratio suggests you're better at networking than shipping.
Research Phase Forever
AURORA's README literally says 'THIS PROJECT IS IN RESEARCH PHASE.' VIDE has no source code. Aurora-Risk-Architecture is a 19KB prototype. You have a graveyard of good ideas that never graduated from README to reality.
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% weight72B
- Depth15% weight65C
- Breadth10% weight55D
- Community10% weight55D
03 · Stats
365-day commit heatmap
265 active days
Language distribution
- Jupyter Notebook94%
- Python3%
- TypeScript1%
- Go1%
- HTML0%
- Astro0%
- Other1%
04 · Numbers
Owned repos
non-fork
26
Commits
last 12 months
598
Followers
339
Joined GitHub
Oct 2024
05 · Top repos
DsThakurRawat /
open-ev-code-handler
AI code review benchmark environment with 30 Python scenarios, typed Pydantic models, FastAPI server, comprehensive CI/CD, and deterministic graders for bug/security/architecture tasks.
DsThakurRawat /
Autonomous-Multi-Agent-AI-Organization
Early-stage polyglot multi-agent AI orchestration platform with typed Python agents, Go backend DAG engine, Kafka messaging, and production-grade architecture patterns—actively developed across 3+ languages with comprehensive docs but limited adoption (8 stars).
DsThakurRawat /
Appscrip
FastAPI investment analysis service with JWT auth, rate limiting, and Gemini AI integration. Well-documented with security patterns, but 0 stars, repo is 3 days old (created 2026-03-24), and no CI pipeline.
DsThakurRawat /
ML-NETWORK-SECURITY-SYSTEM
ML network security pipeline with MongoDB ingestion, sklearn transformers, and MLflow tracking. Structured codebase with typed entities but minimal documentation and no tests. Personal learning project, in development phase.
DsThakurRawat /
instance-segmentation-inpainting-system
Personal project combining Mask R-CNN, DeepFillv2, and PyQt GUI for object removal. Functional proof-of-concept with untyped Python, minimal documentation beyond README, no tests or CI, and limited structured layout across incomplete source files.
DsThakurRawat /
anythingtopdf
One-day-old PDF converter with polished Next.js + Go + Python architecture, security hardening, and CI pipeline. Well-typed and documented but untested, zero adoption, and only a proof-of-concept sprint.
DsThakurRawat /
Aurora-Risk-Architecture
Fresh prototype implementing fair credit scoring for unbanked populations using hand-coded logistic regression and fairness metrics. Structured codebase with tests, clear mission, but created within 4 minutes and under 19 KB—early-stage experimental project with aspirational scope.
DsThakurRawat /
VerilogProcessor
Educational MIPS processor Verilog implementation with FSM-based multi-cycle pipeline. Single source file (~200 LOC), preset instruction/data caches, and functional but minimal scope. No tests, CI, or external adoption signals.
DsThakurRawat /
facial-attractiveness-analyzer
Facial attractiveness prediction project using landmarks, ratios, and Gabor filters. Minimal evidence of shipping: no tests, no CI, no license, untyped Python, sparse commits (7 of last 30), and no source files accessible for review.
DsThakurRawat /
DsThakurRawat
GitHub profile configuration repository with minimal documentation, no meaningful code output, and no clear purpose beyond personal setup files.
DsThakurRawat /
VIDE-AI-ENABLED-VIDEO-AND-IMAGE-EDITOR
Ultra-early-stage monorepo scaffold (2KB, 2 commits in 3 days) with architectural vision but no source code committed. README describes a multi-component AI video editor but no actual implementation present in repo.
DsThakurRawat /
AURORA
Minimal research-phase scaffold with 1KB codebase, 2 commits, no source files sampled, no tests, CI, or license. README states "IN RESEARCH PHASE" with no substantive project direction.
06 · Timeline
- Oct 31, 2024Joined GitHub
- Jun 4, 2025Created DsThakurRawat — Config files for my GitHub profile.
- Jul 9, 2025Created ML-NETWORK-SECURITY-SYSTEM
- Sep 2, 2025Created facial-attractiveness-analyzer
- Oct 27, 2025Created VerilogProcessor
- Dec 16, 2025Created instance-segmentation-inpainting-system
- Mar 2, 2026Created Autonomous-Multi-Agent-AI-Organization — An interaction-driven multi-agent architecture where autonomous agents collaborate to execute tasks across software systems and devices.
- Mar 13, 2026Created Aurora-Risk-Architecture
- Mar 19, 2026Created VIDE-AI-ENABLED-VIDEO-AND-IMAGE-EDITOR — AI ENABLED VIDEO AND IMAGE EDITOR
- Mar 24, 2026Created Appscrip
- Mar 27, 2026Created open-ev-code-handler — A CODE HANDLER FOR YOUR ALL GITHUB REPO
- Apr 6, 2026Created AURORA — AI ON COMMAND
- Apr 6, 2026Created anythingtopdf — convert any thing to pdf
- Apr 24, 2026Most recent push to Autonomous-Multi-Agent-AI-Organization
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.