Skip to content
View justi's full-sized avatar
77 followers ยท 117 following

Achievements

Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: StarstruckAchievement: YOLOAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: StarstruckAchievement: YOLOAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Organizations

@spree @Okazjum @GetBadges @EnviroMonitor

Block or report justi

Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
justi/README.md

Hi, I'm Justyna ๐Ÿ‘‹

๐Ÿ“ Poznaล„, Poland | ๐Ÿ’Ž Ruby on Rails Engineer | ๐Ÿš€ Building production apps

Ruby Rails JavaScript Python PostgreSQL pgvector Hotwire Tailwind Codex Claude Ollama OpenCode macOS Web

Full-stack Rails developer shipping production apps - from health tools and EdTech to SaaS platforms and marketing automation. AI-assisted, human-driven.

Production Projects

  • ๐Ÿ›’ Snipe Sale ๐Ÿ‡ฌ๐Ÿ‡ง๐Ÿ‡ต๐Ÿ‡ฑ๐Ÿ‡ซ๐Ÿ‡ท๐Ÿ‡ฉ๐Ÿ‡ช๐Ÿ‡ช๐Ÿ‡ธ๐Ÿ‡ฎ๐Ÿ‡น - Track promotions from niche shops, not products - 6 country markets
  • ๐Ÿฅ‘ KetoLabs.pl ๐Ÿ‡ต๐Ÿ‡ฑ - Keto/LCHF/LCHP education hub - built it because I follow LCHF myself
  • โœ๏ธ OutlineShare ๐Ÿ‡ฌ๐Ÿ‡ง - LinkedIn content workflow: write, schedule, publish, grow
  • ๐Ÿ“ CramZap ๐ŸŒ / Odpytywarka.pl ๐Ÿ‡ต๐Ÿ‡ฑ - Upload a PDF, get an interactive quiz (OpenAI-powered) - 11 language versions
  • ๐Ÿ” HybridRanking ๐Ÿ‡ฌ๐Ÿ‡ง - SEO auditing tool with real-time analysis
  • ๐Ÿ“š Conftrace ๐Ÿ‡ฌ๐Ÿ‡ง - Research papers from 36 top CS/AI conferences: search, authors, topics, trends - built on my researchpooler fork (of karpathy's)
  • ๐ŸŽญ PersonaTool ๐Ÿ‡ฌ๐Ÿ‡ง - Product-market fit testing with LLM-generated synthetic personas
  • ๐Ÿ“– Anglofaza ๐Ÿ‡ต๐Ÿ‡ฑ - Learn English with fresh BBC articles (OpenAI-powered) - my first AI-driven project (2023)

Open Source

  • ๐Ÿ“œ ruby_llm-contract - Validate and retry LLM outputs for ruby_llm: describe the expected JSON, fall back to a stronger model, gate CI on regressions (demo)
  • ๐Ÿ–ฅ๏ธ Aya - Desktop workspace for long-lived coding-agent terminals (Claude Code, Codex, Aider, ...) - co-author, with @khasinski
  • ๐Ÿงญ ollama-task-router - Task-based prompt router for Ollama: a small model classifies each prompt and routes it to the best local specialist
  • โšก ollama-bench - Reproducible, zero-dependency benchmark of local LLMs: speed (tok/s), energy, reasoning and code quality
  • ๐Ÿ” ollama-agentic-loop - Benchmark of local agentic coding: test-feedback loop over Ollama + solve@K scorer
  • ๐Ÿ”’ claude-code-project-boundary - Claude Code plugin: scope-aware protection for destructive ops within project boundaries
  • ๐Ÿ’ช stimulus-password-strength - Importmap-friendly Rails 8 password strength field with Stimulus & zxcvbn
  • ๐Ÿ’ฐ PriceScanner - Ruby gem for multi-currency price extraction from text
  • ๐Ÿงน no_comments - Ruby gem that strips unnecessary comments from .rb files, leaving code clean for deployment
  • ๐Ÿ“ท xiaomi-cw300-unifi - Bridge a cloud-locked Xiaomi CW300 camera into UniFi Protect via go2rtc + a minimal ONVIF adapter
  • ๐Ÿ”— Contributor to langchainrb - merged fix for Chroma vector search queries (#890, released in 0.19.3)
  • ๐Ÿ”ญ Contributor to MulensModel - gravitational microlensing modeling in Python: 13 merged PRs (CI setup, bug fixes, test coverage)
  • ๐Ÿ“Š Contributor to ccusage - co-authored fix: honor --since/--until in the OpenCode SQLite loader (#1492)

What I'm About

  • Rails 8 all the way - Hotwire, Turbo, Stimulus, no heavy JS frameworks needed
  • AI-augmented development - Claude Code (agents, skills, commands, hooks) and OpenAI to ship faster
  • Local LLMs too - benchmarking and routing local models on Ollama, measured, not guessed
  • Ship it - from idea to production in days, not months
  • Solo founder mode - designing, building, deploying, and marketing entire products

Connect

Twitter LinkedIn Website GitHub

I architect, direct UX, and orchestrate AI agents - they code, I steer. Powered by Polish coffee โ˜•

Pinned Loading

  1. claude-code-project-boundary claude-code-project-boundary Public

    Claude Code plugin: scope-aware protection โ€” allows destructive ops (rm, mv, chmod) within project, blocks them outside. Built for dangerouslySkipPermissions mode.

    Shell 90 3

  2. ruby_llm-contract ruby_llm-contract Public

    Validate and retry LLM outputs for ruby_llm. Describe the JSON response you expect, fall back to a stronger model when the cheaper one fails the rules, and gate CI on regressions โ€” all as one contrโ€ฆ

    Ruby 35

  3. khasinski/aya khasinski/aya Public

    Tabbed terminal manager for coding agents (Claude Code, Codex, shell). Real PTYs, project-grouped tabs, search-everything, theme import.

    TypeScript 20 4

  4. ruby_llm-contract_demo ruby_llm-contract_demo Public

    Companion demo for ruby_llm-contract showing the LLM-as-judge pattern: build โ†’ calibrate โ†’ gate. Polish e-commerce chatbot scenario, live OpenAI calls (gpt-4.1-mini).

    Ruby 3

  5. ollama-task-router ollama-task-router Public

    Task-based prompt router for Ollama: a small model classifies each prompt and routes it to the best of three local specialists (coder / reasoner / quick).

    Python 2

  6. ollama-bench ollama-bench Public

    Reproducible, zero-dependency benchmark of local LLMs on Ollama: speed (tok/s), energy, reasoning and code quality, driven by a single-source-of-truth config pipeline.

    Python 2