Skip to content
View kurkul608's full-sized avatar

Block or report kurkul608

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
kurkul608/README.md

Hi, I'm Petr Molchanov 👋

Senior AI Engineer • LLM agents, RAG, MCP, evals • TypeScript & Python • Full-stack (React, Node.js) • Buenos Aires, Argentina

✍️ I write about building agents at molchanov.blog


👨‍💻 What I do

  • 🤖 Production coding agent (ROGII): I built and operate an autonomous multi-agent coding system in production. It picks up Jira tasks, writes the fix, passes independent AI review and opens merge requests. I also built its human-in-the-loop guardrails, its Retrieval-Augmented Generation (RAG) layer over project docs and code history, and the evals that measure its quality. Stack: Claude Agent SDK, TypeScript, Docker.
  • 🛠 Agent skills for the team: I wrote reusable agent skills that moved QA from manual to agent-driven Playwright e2e testing and sped up onboarding of new engineers.
  • 📊 LLM pipelines with evals (independent work): for a B2B parts marketplace I built a tiered pipeline: rules first, then local classifiers, then a hosted LLM with OpenRouter fallback. It runs 20+ AI features with Zod-validated structured outputs and Langfuse tracing, an eval suite over 1,300+ labeled examples, and a read-only Model Context Protocol (MCP) server.
  • 🔎 Multi-agent research: I built a Claude Code multi-agent research system for company research. An orchestrator plans the work and checks the results, and 8 subagents research in parallel. One run maps a company's subsidiaries and contractors, then tests hypotheses about it against public sources. An open-source version is in progress.
  • 🧩 Before AI, full-stack and UI engineering: I built the React/TypeScript UI for an oil & gas geosteering platform (Canvas 2D well cross-sections, Leaflet to Mapbox migration, ArcGIS integration). At ROKO Labs I cut bundle size 15% and page load time 20%, and built a virtualized data grid for 10,000+ rows at 60fps. Backend: Node.js, NestJS, Fastify, Python/FastAPI, PostgreSQL.

📌 Projects

  • Body Double — a self-hosted AI tutor built for ADHD brains. It teaches the open course AI Engineering from Scratch one lesson at a time. Early beta.
  • qwen-image-apple-silicon-bench — Qwen-Image-2.1 benchmark on Apple Silicon (M1 Pro, 32 GB): GGUF quantizations Q4/Q8/F16 via stable-diffusion.cpp; speed, memory and image quality.
  • molchanov.blog — my blog. Astro + React + Feature-Sliced Design on Cloudflare Pages, with a free "Markdown for Agents" layer for AI crawlers and IndexNow on every deploy.
  • Multi-agent research agent — orchestrator + 8 parallel subagents, hypothesis checks, SQLite knowledge base. Open-source version coming.

More on molchanov.blog/projects.


🛠 Stack

TypeScript Python Node.js React NestJS Fastify PostgreSQL Docker Playwright

Claude Agent SDK Claude Code OpenAI API LangChain RAG pgvector MCP LLM Evals Langfuse


🔗 Let's connect

Building agents too? I like comparing notes.

Blog Badge LinkedIn Badge Email Badge Telegram Badge


GitHub activity stats

Pinned Loading

  1. body-double body-double Public

    A self-hosted AI tutor built for ADHD brains - Claude Agent SDK, RAG, TypeScript

    TypeScript

  2. molchanov-blog molchanov-blog Public

    Personal blog of an applied AI engineer: Astro + React + FSD on Cloudflare Pages, with Markdown for Agents and IndexNow

    TypeScript

  3. wheelhouse-client wheelhouse-client Public

    Next.js 15 client for Wheelhouse – Telegram Mini App that lets users browse & enquire about cars.

    TypeScript

  4. course-forge-api course-forge-api Public

    Nest JS backend for a video-centric course platform (Udemy-like)

    TypeScript 1

  5. qwen-image-apple-silicon-bench qwen-image-apple-silicon-bench Public

    Qwen-Image-2.1 benchmark on Apple Silicon (M1 Pro, 32 GB): GGUF quantizations Q4/Q8/F16 via stable-diffusion.cpp, speed, memory and image quality

    Python