01 · Roasts
The 90-Second Architect
llm-memory-os has an ARCHITECTURE.md, a design.md, a STATUS.md, AND a full FAISS vector pipeline — all committed within 90 seconds. That's not development, that's a ctrl+V with extra steps.
Repo Graveyard Groundskeeper
ogtool-dashboard is an unmodified create-vite template. ailab4 is literally 0 KB. You have a GitHub account that partially functions as a trash folder for project ideas you had at 2am.
0 Stars, 5 READMEs
Every repo has a comprehensive README explaining the vision. Zero repos have tests. The documentation-to-working-code ratio suggests you're optimizing for the wrong audience.
Hackathon Tourist
Your best work (prompt-injection-env) was a 7-day hackathon sprint with 30 commits. Your second-best work was a 5-minute single-session push. Sustained effort is not yet in your vocabulary.
1 Follower, 0 Following
You follow nobody and have 1 follower. GitHub is a social platform. You're using it as a private S3 bucket with a public-read policy.
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% weight55D
- Consistency20% weight55D
- Quality20% weight62C
- Depth15% weight50D
- Breadth10% weight55D
- Community10% weight25F
03 · Stats
365-day commit heatmap
18 active days
Language distribution
- Jupyter Notebook81%
- Python10%
- JavaScript4%
- C++3%
- CSS2%
- HTML0%
04 · Numbers
Owned repos
non-fork
13
Commits
last 12 months
36
Followers
1
Joined GitHub
Jul 2025
05 · Top repos
Samyak17Jain /
prompt-injection-env
Specialized OpenEnv-compatible RL environment for prompt injection detection with 30 deterministic tasks (3 difficulty tiers), structured FastAPI server, and deployed Hugging Face Space. Built as hackathon submission with typed Pydantic models, deterministic grader, and multi-context task coverage.
Samyak17Jain /
glyptika-form
Personal project: React + Vite form with multi-step PIQ questionnaire and client-side PDF export via html2canvas + jsPDF CDN. Typed JavaScript, structured src/ layout, comprehensive README. No tests/CI. Minimal public adoption (0 stars). Created 5 days ago, 6 commits sampled.
Samyak17Jain /
llm-memory-os
Memory OS is a modular long-term memory system for AI assistants with extraction, scoring, retrieval, and decay pipelines. ~127 KB Python project created March 2026, shipped with structured docs, typed configuration, and FAISS vector search—but nascent (1 commit in 90 seconds), no tests, no CI/license, and unpublished.
Samyak17Jain /
Trade_Reconciliation_Pipeline
A newly created (3/21/26) Python trade reconciliation pipeline with structured architecture, PostgreSQL schema, and Pandas ETL. Single commit, zero stars. Clear domain-specific tool but early-stage experimental work.
Samyak17Jain /
Backtesting
One-day backtesting engine for momentum strategies in Python. Typed, well-documented with comprehensive README, modular architecture, and full validation workflows (Walk-Forward & CPCV), but brand new with only 2 of 30 commits sampled and zero adoption signals.
Samyak17Jain /
ogtool-dashboard
Minimal React+Vite scaffold with boilerplate README, zero commits of actual work, no tests/CI/license, and no meaningful project files sampled.
Samyak17Jain /
CN_LabAssignments
Empty lab assignment scaffold with zero stars/forks, no README, no documentation, single commit, untyped language. No meaningful code or structure detected.
Samyak17Jain /
ailab4
Empty scaffold with 0 files, created and pushed same day (2026-02-22). No README, tests, CI, license, or source code sampled. Appears to be a one-shot initialization dump with no substantive content.
06 · Timeline
- Jul 7, 2025Joined GitHub
- Jan 26, 2026Created CN_LabAssignments
- Feb 22, 2026Created ailab4
- Mar 21, 2026Created Backtesting
- Mar 21, 2026Created Trade_Reconciliation_Pipeline
- Mar 21, 2026Created llm-memory-os
- Apr 2, 2026Created prompt-injection-env
- Apr 16, 2026Created ogtool-dashboard
- Apr 19, 2026Created glyptika-form
- Apr 24, 2026Most recent push to glyptika-form
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.