Projects
Public GitHub projects + AI tooling ecosystem highlights (Jarvis, destylaty, pipelines).
Code projects
AI QA Manual · Jarvis destylat
Production-ready manual QA workflow extracted from Jarvis. Context-first pipeline: Figma MCP + Jira webhook + Playwright CLI + Claude Agent SDK. Scale: 100-200 tasks in 2-3 days vs team-week classical.
Tech stack
- TypeScript
- Node.js
- Claude Agent SDK
- Playwright
- MCP
- n8n
CDAT Pattern · Playwright architecture
Components-Data-Actions-Tests - 4-layer architectural pattern for Playwright + TypeScript. Alternative to Page Object Model. Battle-tested across 9 production systems over 2 years.
Tech stack
- TypeScript
- Playwright
- Node.js
sdet-wcag-toolkit · Public WCAG 2.2 AA pipeline
Public AGPL-3.0 distillate of multi-agent WCAG audit pipeline. 5 AI specialists reading source via Read/Grep/Glob, plus static TypeScript analyzer and Playwright + axe-core dynamic testing. A-F grading. Case study in From the Field series #01.
Tech stack
- TypeScript
- Claude Agent SDK
- Playwright
- axe-core
- MCP
sdet-brain · Persistent RAG over MCP
Local-first persistent RAG for personal Markdown corpus. Qdrant + MLX + FastAPI + FastMCP 3.0. 12 MCP tools, 213 tests, source-available. Replaces copy-paste of context across Claude Desktop / Code / OpenCode chats.
Tech stack
- Python
- FastAPI
- FastMCP
- Qdrant
- MLX
- MCP
skills-radar · Lazy-loading skill discovery for Claude Code
Open-source MCP server fixing Claude Code skill bloat. Two-Tier Discovery: ~1k token mini-index always preloaded, full SKILL.md loaded on demand. 68% token reduction at 60 skills, roughly flat at 500. Hybrid retrieval (BM25 + dense), trust tiers, 100% local Apple Silicon stack via MLX (Qwen3-Embedding-8B + Qwen3-Coder-30B rewriter/reranker). No Ollama, no HTTP, no network.
Tech stack
- Python
- FastMCP
- ChromaDB
- Qdrant
- MLX
- sentence-transformers
sdet-perf-toolkit · Context-first performance audit
Performance audit for Nuxt3/Vue3. Deterministic floor: Lighthouse median-of-5 + Core Web Vitals via Playwright + trace + bundle. 5 AI specialists for what the floor does not catch. AGPL-3.0.
Tech stack
- TypeScript
- Lighthouse
- Playwright
- web-vitals
jarvis-brain-core · Code-graph context over MCP
Educational distillate of the private jarvis-brain: code-graph + 5 MCP tools, 135/135 tests. The cross-repo context method for agents, on public code. AGPL-3.0.
Tech stack
- Python
- MCP
- SQLite
- FTS5
ai-seo-pack · AI-friendly portfolio kit
Template for an AI-friendly portfolio: robots/llms.txt, .well-known, OG, JSON-LD. So that AI crawlers and classic SEO see the same thing. Astro reference, cross-stack.
Tech stack
- TypeScript
- Astro
- JSON-LD
- llms.txt
five-minds · 5-LLM decision council
CLI council of 5 LLM models (moderator-led, 3+ ecosystems) for hard decisions. Local + API. AGPL-3.0.
Tech stack
- Python
- CLI
- LLM
qa-report-lake · Dual-mode QA report-lake
Deterministic CTRF core - history, trends, flaky-vs-new - plus visual regression (pixel diff, reg-suit baseline), with a removable AI advisory layer proven byte-identical. 25 tests, AGPL-3.0.
Tech stack
- TypeScript
- Node.js
- CTRF
- pixelmatch
- MinIO
flaky-analytics · Flaky-test analytics skill
Zero-dependency Claude Code skill - flake events plus chronic/intermittent/isolated/always-failing classification and a quarantine plan from CI history. AI = Claude in-session, byte-exact dual-mode invariant. 54 tests, AGPL-3.0.
Tech stack
- Node.js
- CTRF
- JUnit XML
- Playwright JSON
- zero-dep
sdet-canvas · Local-first AI design tool (early preview)
Early preview (v0.5.0). Local-first Electron desktop app for AI-driven UI prototyping - an open-source take on Claude Design. Six model providers: Anthropic BYOK, Claude Code / OpenCode subscriptions, OpenRouter, plus local Ollama and MLX. Generates multi-file HTML/CSS/JS workspaces, live design-token inspector, version history, export to HTML/PDF/ZIP. Unsigned binaries (macOS arm64 + Linux) or run from source. Solo-maintained, pre-1.0, not for production.
Tech stack
- Electron
- TypeScript
- React
- Vite
- SQLite
- MLX
Portfolio v1 · Matrix-style legacy
Archived first version of sdet.pl portfolio. React + Framer Motion + Matrix animations. Kept for historical continuity - proves brand presence since early 2025.
Tech stack
- React
- Framer Motion
- Vite
Ecosystem highlights
Private AI tooling ecosystem + open-source destylaty w przygotowaniu.
Jarvis · Production multi-agent QA platform
Private · 34K LOC · 9 microservices · event-driven
Private multi-agent platform powering real-world QA workflows. 9 microservices, event-driven architecture, real-time UI, NATS messaging, PostgreSQL, WebSocket, 15 production pipelines. WCAG 7-agent + Performance 5-agent auditing at production scale. Modules published as standalone destylaty below.
Key metrics
- Lines of code
- 34K
- Microservices
- 9
- Production pipelines
- 15
- UI components
- 57
Jarvis Manual · QA workflow destylat
Context-first pipeline · human-in-the-loop
Open-source destylat of the Jarvis manual QA workflow. Figma MCP + Jira webhook + Playwright CLI + Claude Agent SDK. Human approval checkpoints. Educational, not operational - method shown on dummy data, production integration = 2-4 weeks.
Jarvis Figma · deterministic design pipeline
CSS token mapping · visual diff · codegen spec
Deterministic Figma pipeline. Extract design tokens via Figma MCP (no LLM at data layer), map to CSS variables, diff expected vs computed, pixel-level visual diff via odiff, codegen spec generation. LLM only in logic layer.
Tempo Timesheet · audit & automation destylat
Git commits vs Tempo worklogs · risk scoring
Compare git commits vs Tempo worklogs, detect overtime patterns, risk scoring per developer. Jira + Tempo API integration, scheduled batch sync, human-in-the-loop approval queue.
jarvis-brain · cross-project knowledge vault
Dev meta-tool · stops Claude Code from burning tokens
Private dev tool - cross-project knowledge graph for Claude Code. FastAPI + PostgreSQL + Redis + Docker. 175 tests, mypy strict. MCP server exposes searchable project context so CC doesn't re-scan files on each session.
Key metrics
- Test coverage
- 175
- Phase
- P2-S1