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

#12 — Top 99.1%

Git-on-my-level

David Zhang

A

Ship machine

Overall

0.0

/ 100

01 · Roasts

2,764 Commits and Still Shipping Stubs

You pushed 2,764 commits this year and somehow still found time to create blessed-car-apps (0 files) and demo-qr-generator (abandoned in 31 minutes). The heatmap is a wall of green but some of those squares are suspiciously hollow.

1,523 PRs/Year Is Not a Human Number

You opened 1,523 pull requests in a single year. That's 4.2 PRs per day, every day, including weekends. Either you've automated your own GitHub activity or you are the objective function at scalingforever.com.

License? Never Heard of Her

codex-autorunner has 746 stars and moes-tavern has a full ERC-8004 smart contract suite — but multiple repos are shipping without a LICENSE file. You're out here letting the world use your agent orchestration stack under the legal framework of 'vibes.'

The 4-Following Ratio

183 followers, following 4 people. You have a follower-to-following ratio of 45:1. Either you're a GitHub celebrity or you've fully optimized away social reciprocity in pursuit of the objective function.

Agent Orchestration All the Way Down

codex-autorunner supervises agents, agent-nexus coordinates agents, social-autorunner compiles agent campaigns, moes-tavern is a marketplace for agents, and memc is a memory compiler for agents. David, are you building tools or are the tools building you?

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
    76B
  • Consistency
    20% weight
    95S
  • Quality
    20% weight
    72B
  • Depth
    15% weight
    70B
  • Breadth
    10% weight
    80A
  • Community
    10% weight
    65C

03 · Stats

365-day commit heatmap

323 active days

Less
More

Language distribution

7 langs
  • Python46%
  • C27%
  • TypeScript8%
  • Go7%
  • JavaScript6%
  • Svelte2%
  • Other4%

04 · Numbers

Owned repos

non-fork

38

Commits

last 12 months

2,764

Followers

183

Joined GitHub

Oct 2014

05 · Top repos

Git-on-my-level /

codex-autorunner

68/100

Production-grade Python agent coordination hub with 746 stars, full type safety, comprehensive test/CI suite, multi-surface architecture (web, CLI, chat), and extensive design documentation enabling long-running autonomous workflows across Codex/Hermes/OpenCode.

I65Q75D65
READMETestsCITyped
Python7461mo ago

Git-on-my-level /

agent-nexus

68/100

Well-architected agent coordination monorepo with typed Go backend, SvelteKit UI, and Python bridge runtime. Shipped self-hosted workspace product with comprehensive infrastructure (tests, CI, docs, contracts). 30+ commits over ~2 months shows sustained multi-service development.

I55Q75D65
READMETestsCITyped
Go51mo ago

Git-on-my-level /

ios-mosh-terminal

65/100

iOS Mosh terminal client implementing SSH bootstrap + UDP-based Mosh with managed tmux and auto-reconnect. Typed Swift, structured services, binding design docs (CONSTITUTION.md), CI/tests, ~47 days old, 1 star. Non-trivial portfolio project with shipped architecture and working code.

I40Q75D0
READMECI
C12mo ago

Git-on-my-level /

moes-tavern

50/100

ERC-8004 agent marketplace with typed Solidity contracts + TS packages (curation, search, indexer). Full monorepo with tests, CI, but nascent (created Feb 2026, 18 commits in 1 day, 0 stars).

I40Q60D50
READMETestsCITyped
TypeScript03mo ago

Git-on-my-level /

demo-web-agent-harness

45/100

A self-contained web agent harness demo in vanilla JS with a sandboxed LLM tool-execution loop. Typed config, modular architecture, and persistence—but no tests, CI, or production signals. Personal experimental project showing working proof-of-concept.

I25Q55D50
README
JavaScript31mo ago

Git-on-my-level /

memc

45/100

Early-stage personal project: memory compiler for agent workflows. Typed Rust with structured docs (ARCHITECTURE.md, LANGUAGE_SPEC.md), CLI tool, parser, compiler, and recall engine—shipped as v0.1.0 with CI/release workflow. Non-trivial scope but nascent (0 stars, <30 commits).

I25Q60D50
READMECITyped
Rust01mo ago

Git-on-my-level /

crimson-web-port

45/100

TypeScript+Vite web port of Crimson game using Phaser 3, with documented architecture, CI/tests, and live demo—early-stage personal project showing structured development but nascent adoption.

I25Q60D50
READMETestsCITyped
C03mo ago

Git-on-my-level /

social-autorunner

42/100

Python CLI tool for social media campaign management with structured compilation workflow, SQLite backend, LLM provider integration, and comprehensive config schema. Early-stage project (1 star, <2 months old) with working typed code, good test coverage, and published documentation.

I25Q55D50
READMETestsCI
Python12mo ago

Git-on-my-level /

vibe-evm

38/100

Python EVM investigation SDK designed for LLM agent workflows. Includes workspace CLI, typed clients (RPC/Etherscan/Tenderly), caching, budgeting, and artifact management. Well-documented with ARCHITECTURE.md and design patterns, but nascent (2 stars, minimal recent commits, no tests/CI).

I25Q55D35
README
Python22mo ago

Git-on-my-level /

car-ticket-templates

30/100

Minimal template repository for Codex Autorunner (CAR) with plain Markdown ticket templates. 2 stars, 6 commits in 2.5 months, no tests/CI/license. README explains purpose and conventions, but lacks code samples or deep architecture.

I25Q50D20
README
Unknown21mo ago

Git-on-my-level /

demo-qr-generator

7/100

Minimal HTML project with zero documentation, tests, or CI. Created and abandoned within 31 minutes with 3 commits. No meaningful architectural scope or ongoing investment detected.

I5Q10D5
HTML01mo ago

Git-on-my-level /

blessed-car-apps

3/100

Empty repository with initial commit only, no files, no documentation, no code. Not yet a project.

I5Q0D5
Unknown01mo ago

06 · Timeline

  1. Oct 24, 2014
    Joined GitHub
  2. Dec 9, 2025
    Created codex-autorunner
  3. Dec 25, 2025
    Created vibe-evm — A prescriptive way for LLM agents to analyze EVM state and transactions
  4. Jan 27, 2026
    Created ios-mosh-terminal
  5. Feb 1, 2026
    Created car-ticket-templates
  6. Feb 4, 2026
    Created crimson-web-port
  7. Feb 6, 2026
    Created social-autorunner
  8. Feb 11, 2026
    Created moes-tavern — ERC-8004-aligned agent marketplace
  9. Mar 5, 2026
    Created agent-nexus
  10. Apr 17, 2026
    Created demo-qr-generator — Fun QR code generator — custom colors, sizes, WiFi presets, PNG/SVG export
  11. Apr 17, 2026
    Created demo-web-agent-harness — Self-modifying web agent demo, a self contained web agent harness
  12. Apr 21, 2026
    Created memc
  13. Apr 29, 2026
    Created blessed-car-apps
  14. Apr 30, 2026
    Most recent push to codex-autorunner

07 · Compare

github.com/
Git-on-my-level · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total77.4
Top-end curve+5.4
Final overall82.8

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.
Git-on-my-level · 82.8/100 — Rate My GitHub