01 · Roasts
Sprint Addict, No Finisher
You've shipped 9+ repos in under 6 weeks, each abandoned within 1–4 days of creation. tradingbot, lend, agent_data, agentic_commerce — all born, 20 commits, then radio silence. The graveyard opens fast around here.
README Hallucinator
neuralcore promises TLA+ formal verification, Nitro Enclaves, and distributed consensus in its README — the code is commented-out stubs. Your READMEs are writing checks your git log can't cash.
Zero Social Existence
0 followers, 0 following, soloPct=99%. You've committed 1,436 times this year and not a single human has noticed. You're not building in public, you're building in a sealed bunker.
The CSS Enigma Named '23'
A 22 MB CSS repo, 30 commits in 13 hours, README that says only '# 23'. This is either performance art or a git accident — either way it's in your public portfolio.
One Star Wonder
Across 52 public repos and 1,436 commits, you've accumulated 64 total stars — 44 of which belong to a single repo (translator). The other 51 repos share 20 stars between them. Quality > quantity, friend.
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% weight60C
- Breadth10% weight65C
- Community10% weight25F
03 · Stats
365-day commit heatmap
93 active days
Language distribution
- Python55%
- TypeScript29%
- HTML9%
- JavaScript4%
- CSS1%
- Go1%
- Other1%
04 · Numbers
Owned repos
non-fork
42
Commits
last 12 months
1,436
Followers
0
Joined GitHub
Aug 2025
05 · Top repos
kwstx /
translator
Production-scale agent middleware with protocol translation, self-healing schemas, and hybrid MCP+CLI routing. Well-structured FastAPI backend + Python SDK, comprehensive docs (ARCHITECTURE.md, design.md), and working CI. Spans 72 MB across server & SDK with typed async patterns, security (JWT+EAT), and ML-driven optim
kwstx /
kyb_agent
Personal KYB (Know Your Business) agent built with LangGraph, LLMs, and async Python. Has structured architecture with agents, tools, safety guardrails, and API, but lacks README, tests pass syntax checks, no CI, minimal adoption signals (0 stars/forks), created 2 days ago.
kwstx /
agent_money
Early-stage multi-service financial orchestration platform for AI agents. Typed Go/Python with Redis/Postgres, spans 5+ microservices, policy engine, and async metering. Structured codebase shows ambition but minimal adoption signal (1 star, 1 day old).
kwstx /
agentic_commerce
Early-stage multi-agent e-commerce platform with structured architecture (LangGraph, FastAPI, async patterns) and alternate docs, but experimental code, no tests, missing license, and under 1 month old with incomplete implementations.
kwstx /
tradingbot
Young Python trading bot with LangGraph multi-agent architecture for Polymarket weather arbitrage. Untyped, minimal tests/CI, but has SQLite persistence, Bayesian priors, backtesting, and documented setup. Created mid-April 2026, 523 KB, 20 recent commits.
kwstx /
lend
Early-stage fintech lending platform with real business logic (cash-flow analytics, risk engine, repayment automation), typed Python, structured services, and documented architecture. No external adoption (0 stars/forks), ~4 weeks of work with 18 recent commits on fresh codebase.
kwstx /
agent_data
Early-stage experimental protocol for verifiable real-time data access. Implements a Rust-based node with Merkle tree consensus, Python SDK, and Solidity anchor. Lacks tests, CI, and production maturity despite solid technical scope.
kwstx /
landing_page
Minimal landing page project in HTML with sparse documentation and no tests. 30 commits over ~6 weeks show some iteration, but thin output and experimental scope limit overall assessment.
kwstx /
kyb_page
A static HTML/CSS landing page for Asset platform, 4.5MB codebase with 20 commits over 4 days. No tests, CI, license, or gitignore; vanilla frontend without typed tooling or production infrastructure.
kwstx /
neuralcore
Ambitious but hollow distributed AI system with zero stars. Grandiose README promises TLA+ verification, formal proofs, and Nitro Enclaves, but code is mostly commented-out stubs, mocked dependencies, and aspirational imports. Created and last pushed same day (Apr 26, 2026). No architectural coherence between readme cl
kwstx /
kwstx
Profile README with no shipping code. Empty repo containing only a bio and tech badges, no implementation, tests, or CI. Describes agent economy interest but has zero demonstrated output.
kwstx /
23
Minimalist CSS repo with near-empty README ("# 23"), 22 MB untyped content, no tests/CI/license, 30 commits in single day (2026-04-15). Appears to be a one-off experimental dump.
06 · Timeline
- Aug 9, 2025Joined GitHub
- Feb 27, 2026Created landing_page — translator landing page
- Mar 9, 2026Created translator — layer that lets you connect any agent, any tool, any api together.
- Mar 12, 2026Created kwstx
- Apr 15, 2026Created 23
- Apr 17, 2026Created lend
- Apr 18, 2026Created tradingbot
- Apr 19, 2026Created agent_data
- Apr 24, 2026Created agentic_commerce — Autonomous multi agent platform for product discovery, comparison, and checkout.
- Apr 26, 2026Created neuralcore
- Apr 29, 2026Created agent_money — unified interface for agents to execute expenditures
- Apr 30, 2026Created kyb_agent
- May 2, 2026Created kyb_page
- May 6, 2026Most recent push to kyb_page
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.