▸ This tool was built by an AI agent from Zoral
← RATE MY GITHUB

#149 — Top 87.6%

Flamki

Ayush Singh

C

Getting there

Overall

0.0

/ 100

01 · Roasts

The Invisible Contributor

Bio proudly reads 'Open Source Contributor @ Jenkins & YC Startup' yet the public record shows 0 PRs, 0 issues, and 0 followers in the past year. The contributions may be real — but they're hiding harder than your commits.

Speed Coder, Ghost Deployer

9 of your 12 analyzed repos were built in under 24 hours. vibe-code-cup was literally committed in 2 minutes and 11 seconds. You ship fast and disappear faster — a hackathon assembly line with no one waiting at the finish line.

CI? That's Someone Else's Problem

Only 2 of 12 repos have CI. vaultVK with a C++ distributed system has a pipeline; stellarmind, flamki-vector-search, and kavachai — all perfectly capable of one — do not. The tests you did write have no one running them automatically.

101 Repos, 1 Star

You've published 101 public repositories since August 2022 and accumulated a grand total of 1 star. At this rate, you'll hit 100 stars sometime around 2122. Quality over quantity is a policy, not a suggestion.

The Heatmap Void

Your public contribution heatmap is 52 consecutive weeks of pure zeros. Even accounting for private work, that's a GitHub profile that looks like it was abandoned mid-thought. The resume says active; the graph says otherwise.

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

  • Impact
    25% weight
    68C
  • Consistency
    20% weight
    60C
  • Quality
    20% weight
    62C
  • Depth
    15% weight
    55D
  • Breadth
    10% weight
    80A
  • Community
    10% weight
    25F

03 · Stats

365-day commit heatmap

0 active days

Less
More

Language distribution

7 langs
  • TypeScript29%
  • Python27%
  • Jupyter Notebook25%
  • JavaScript10%
  • C++2%
  • CSS2%
  • Other5%

04 · Numbers

Owned repos

non-fork

40

Commits

last 12 months

0

Followers

0

Joined GitHub

Aug 2022

05 · Top repos

Flamki /

vaultVK

52/100

A 177 KB distributed key-value system with C++17 engine, FastAPI gateway, React frontend, Docker Compose stack, and comprehensive CI/CD. Typed, tested, documented, and live-deployed but brand-new (created 2026-03-19, 16 recent commits).

I25Q65D50
READMETestsCITyped
TypeScript02mo ago

Flamki /

incident-autopilot

48/100

Full-stack incident response platform prototype with typed Python/TypeScript, documented architecture, CI/tests, and live deployments—but nascent (2 days old, 20 commits) with zero external adoption or named product positioning.

I25Q60D50
READMETestsCITyped
TypeScript02mo ago

Flamki /

shadowswap

42/100

Early-stage privacy-focused DEX prototype with React frontend + Solidity smart contracts using FHE encryption. TypeScript + tests present but limited production readiness; experimental burst of work across 7 commits in <24 hours.

I25Q65D35
READMETestsTyped
TypeScript02mo ago

Flamki /

content-broadcasting-system

40/100

Young Node.js/Express backend with JWT auth, PostgreSQL/Prisma, Redis caching, and role-based content approval workflow. Well-documented with ARCHITECTURE.md and OpenAPI spec, but minimal commit history and zero adoption.

I25Q60D35
READMETests
JavaScript01mo ago

Flamki /

vectorshift-frontend-technical-assessment

38/100

Technical assessment submission implementing a React-based pipeline node editor with 10+ node types, dynamic templating, Zustand state management, FastAPI backend with DAG validation, and 569 KB of working code—complete but undeployed, no tests, no CI.

I25Q55D35
README
JavaScript01mo ago

Flamki /

flamki-vector-search

38/100

Hackathon project: local-first multimodal semantic search (text, image, audio) with FastAPI, CLIP embeddings, and Actian VectorAI DB. Shipped working demo with 2,781 files indexed; spans 3 stages (parsing, embedding, search) and includes React PWA. Early-stage codebase without tests, CI, or license.

I25Q50D35
README
Python01mo ago

Flamki /

meetingmind-plusplus-airia

38/100

Personal Python project integrating meeting transcripts with Airia API and fanout to Slack/Jira/Email. Typed code, structured multi-file layout, docs, tests, but brand-new (3d old), minimal stars/adoption, unpolished finish (incomplete README, no license).

I25Q50D35
READMETests
Python02mo ago

Flamki /

kavachai

35/100

TypeScript/Python security scanning app (URL/email/hash analysis) with FastAPI backend, React frontend, and integrations to VirusTotal, URLScan, GSB. Typed, documented, structured but nascent—created 2026-03-25, 7 commits, no tests/CI/license.

I25Q50D25
READMETyped
TypeScript02mo ago

Flamki /

vibe-code-cup-challenge1-public-copy

32/100

A competition entry implementing a chess AI agent with negamax search, tapered evaluation, Zobrist hashing, and null-move pruning. Well-documented submission with test coverage and deterministic guarantees, but created as a one-off challenge response with 12 recent commits over ~2.5 minutes.

I15Q60D20
READMETests
JavaScript01mo ago

Flamki /

stellarmind

25/100

Early-stage AI agent marketplace on Stellar testnet with x402 payments. JavaScript project with MIT license and README, but no tests, CI, or type safety. Created Apr 2026 with 21 of 30 recent commits (single-week sprint).

I15Q40D20
README
JavaScript01mo ago

Flamki /

schemesaathi

15/100

Hackathon submission (created 2026-03-22, 4 commits in ~41 min) for AI-powered welfare scheme discovery. 46 KB untyped JavaScript, no tests/CI/license, minimal source samples. Early-stage experimental project.

I15Q25D5
README
JavaScript02mo ago

Flamki /

devmind

12/100

One-shot generated scaffold for Gemini API integration; minimal code (69 KB), single commit, no tests/CI. Appears to be AI-generated boilerplate from a hosted service rather than a sustained project.

I5Q25D5
READMETyped
TypeScript02mo ago

06 · Timeline

  1. Aug 20, 2022
    Joined GitHub
  2. Mar 17, 2026
    Created devmind
  3. Mar 18, 2026
    Created meetingmind-plusplus-airia
  4. Mar 19, 2026
    Created vaultVK
  5. Mar 22, 2026
    Created schemesaathi
  6. Mar 23, 2026
    Created shadowswap
  7. Mar 24, 2026
    Created incident-autopilot
  8. Mar 25, 2026
    Created kavachai
  9. Apr 11, 2026
    Created vibe-code-cup-challenge1-public-copy
  10. Apr 12, 2026
    Created stellarmind — AI Agent Marketplace with x402 Micropayments on Stellar — Claude-powered agents that buy, sell, and earn autonomously
  11. Apr 19, 2026
    Created flamki-vector-search — Flamki Vector Search: local-first multimodal search with Actian VectorAI DB
  12. Apr 26, 2026
    Created content-broadcasting-system — Content Broadcasting System - Backend API with Node.js, Express, PostgreSQL, JWT Auth, RBAC, Redis Caching, and Subject-based Content Rotation
  13. May 3, 2026
    Created vectorshift-frontend-technical-assessment
  14. May 3, 2026
    Most recent push to vectorshift-frontend-technical-assessment

07 · Compare

github.com/
Flamki · 6dmedian coder

08 · Rubric

How this score was produced

Overall = Σ (category × weight) + gentle top-end curve

CategoryWeightScoreContrib.
Raw total60.1
Top-end curve+4.9
Final overall65.1

Tier thresholds

S90100Mass-producing humansA8089Ship machineB7079Solid engineerC6069Getting thereD4059README enthusiastF039GitHub tourist
▸ How the pipeline works
  1. 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.
  2. 02Triage.A small model reads every repo's file tree + README and picks the 20 files per repo that actually reveal how you code.
  3. 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.
  4. 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.
  5. 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.
Flamki · 65.1/100 — Rate My GitHub