01 · Roasts
Sprint King, Ghost Town
9+ repos, 3 total stars, 0 forks. autoops_ai has a full ARCHITECTURE.md, SYSTEM_DESIGN.md, STATUS.md, and exactly 1 star — from what appears to be the author. You document better than you deploy.
13-Minute Monorepo
ai_education: Next.js + Hono + Durable Objects + AI tutor + VR classroom + proctoring — all scaffolded in 13 literal minutes across 5 commits. The README promises 14 features; the code delivers a truncated interview.ts function.
The Same-Day Repo Pattern
speech_to_speech was created and last pushed the same day, 42 minutes apart. speech_assistent got 8 days. agentic_cicd got 2. You're incubating ideas faster than they can compile.
No Tests, No CI, No Problem (Apparently)
11 of 12 repos have no tests. 10 of 12 have no CI. The one exception (autoops_ai) gets a CI badge and you still shipped it 5 weeks ago with 0 forks. The quality pipeline is in DESIGN.md, not .github/workflows.
Mock Data in Production Claims
agentic_cicd's github.go has FetchPipelineLogs returning a hardcoded string and CreatePullRequest silently creating an Issue instead. The README says 'production-grade autonomous pipeline repair.' These are not the same thing.
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% weight60C
- Quality20% weight57D
- Depth15% weight55D
- Breadth10% weight80A
- Community10% weight55D
03 · Stats
365-day commit heatmap
58 active days
Language distribution
- TypeScript30%
- JavaScript27%
- Python25%
- CSS15%
- HTML1%
- PowerShell1%
- Other1%
04 · Numbers
Owned repos
non-fork
26
Commits
last 12 months
211
Followers
11
Joined GitHub
Sep 2023
05 · Top repos
adithya11sci /
autoops_ai
TypeScript multi-agent DevOps AI system with LangGraph orchestration, risk assessment, and command validation. Typed, documented with ARCHITECTURE.md, has tests and CI. Early-stage prototype (1 star, created March 2026) with ambitious scope but nascent adoption.
adithya11sci /
synapt.ai_agentic_rag
Standalone agentic RAG system for Indian IT company financials combining LLM tool routing, vector search, structured data queries, and web search—well-documented but unshipped/zero adoption with no tests or CI.
adithya11sci /
movie_ticket_bookings
MERN movie booking system with atomic seat locking, concurrent booking prevention, and admin controls. Well-documented with design files; no tests or CI. ~18.5 MB codebase built over ~55 days with structured backend architecture.
adithya11sci /
agentic_cicd
Early-stage agentic CI/CD system in Go with multi-agent orchestration (Monitor, RootCause, Repair, Governance, PR agents) for autonomous pipeline repair. Typed, documented README, structured modular layout (cmd/, internal/agents/, internal/services/), but very new (2 days old), no tests, no CI, lacks production-grade e
adithya11sci /
inter_view
Personal project: 3D animated interview coach with React+Three.js frontend, Node/FastAPI backend. Typed JavaScript, documented README, structured codebase (23.5 MB, ~10k LOC estimated), but minimal adoption (1 star, no external engagement).
adithya11sci /
ai_chat_bot_for_csv
Early-stage Python RAG chatbot for CSV analysis using FastAPI, FAISS, and Groq LLM. Typed with structured layout, good documentation, but minimal stars/adoption and thin test coverage.
adithya11sci /
railway_track_management_system
Early-stage multi-agent railway AI system with comprehensive documentation (README, ARCHITECTURE.md, design.md, docs/) and untyped Python code; 9 commits over ~3 months, zero stars, no tests/CI/license.
adithya11sci /
speech_to_speech
Voice avatar system with ASR→LLM→TTS pipeline. Has architecture docs (design.md, ARCHITECTURE.md, STATUS.md) and documented roadmap, but created today with minimal commits (4 of last 30), untyped Python, no tests or CI, no license. Early-stage experimental project.
adithya11sci /
ai_education
Fresh monorepo for AI-powered educational platform with Next.js frontend + Hono backend. Typed, structured, and documented—but extremely early-stage (5 commits in 13 minutes, created 2026-03-20) with zero adoption signals.
adithya11sci /
speech_assistent
Early-stage conversational AI avatar project with lip-sync pipeline (Groq LLM + Wav2Lip). 134 KB codebase, 6 commits in 8 days, documentation present but no tests/CI; untyped Python with minimal source samples.
adithya11sci /
adithya11sci
Empty personal profile repo with only a README. No source code, tests, CI, or meaningful project output—just a self-introduction and tech stack badges.
adithya11sci /
agentic-demo-target
Empty scaffold created 2026-03-15 with only CI workflow, no code, no README, no documentation. Single commit representing initial repo setup.
06 · Timeline
- Sep 16, 2023Joined GitHub
- Dec 17, 2025Created railway_track_management_system
- Jan 19, 2026Created adithya11sci
- Jan 28, 2026Created inter_view
- Feb 2, 2026Created movie_ticket_bookings
- Feb 18, 2026Created ai_chat_bot_for_csv
- Feb 25, 2026Created speech_assistent
- Mar 11, 2026Created speech_to_speech
- Mar 14, 2026Created agentic_cicd
- Mar 15, 2026Created agentic-demo-target
- Mar 20, 2026Created ai_education
- Mar 31, 2026Created autoops_ai
- Apr 20, 2026Created synapt.ai_agentic_rag
- May 4, 2026Most recent push to autoops_ai
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.