# Roman Matveev
> Portfolio and case studies for Roman Matveev. I take rough briefs and turn them into services: APIs, integrations, automation, and LLM features.
> Languages: English (/en), Russian (/ru), Simplified Chinese (/zh). Default route locale: /en.

## Locale indexes
- [Russian llms.txt](https://ramenm.com/ru/llms.txt)
  - llms-full.txt: https://ramenm.com/ru/llms-full.txt
- [English llms.txt](https://ramenm.com/en/llms.txt)
  - llms-full.txt: https://ramenm.com/en/llms-full.txt
- [Simplified Chinese llms.txt](https://ramenm.com/zh/llms.txt)
  - llms-full.txt: https://ramenm.com/zh/llms-full.txt

## Preferred entry points
- [English home markdown](https://ramenm.com/en/index.md)
- [English chat markdown](https://ramenm.com/en/chat/index.md)
- [English resume PDF](https://ramenm.com/resumes/en/master.pdf)
- [Sitemap](https://ramenm.com/sitemap.xml)
- [llms-full.txt](https://ramenm.com/llms-full.txt)

## Featured case studies
- [nnzen model catalog](https://ramenm.com/en/projects/llm-models-hub/index.md) - A live catalog with 500+ model cards that makes model research less scattered.
  - Impact: Model choice went from tab-hopping to one place.
  - Stack: Python, FastAPI, LLM APIs, RAG, Vector DB / pgvector, Tool calling
- [Custom Agent Core with MCP](https://ramenm.com/en/projects/enhanced-mcp-agent/index.md) - LLM core with a plugin execution layer for a developer assistant: hot reload, tool chains, and explicit context handoff.
  - Impact: The result is a reusable core that can support new workflows and tools without a full rewrite.
  - Stack: Python, FastAPI, MCP, Tool calling, LLM APIs, Docker / Docker Compose, TypeScript
- [Trading Automation for an In-Game Marketplace](https://ramenm.com/en/projects/marketplace-trading-bot/index.md) - Automation for a constrained external marketplace with strategy logic, execution control, and logging.
  - Impact: The system could keep running under platform changes instead of falling apart.
  - Stack: Python, FastAPI, REST APIs / Webhooks, Reverse engineering, Docker / Docker Compose
- [Resilient Data Collection Tooling](https://ramenm.com/en/projects/resilient-data-collection/index.md) - Data extraction tooling for a changing web environment with persistent anti-bot friction.
  - Impact: Less firefighting, more predictable extraction.
  - Stack: Python, Web scraping, Reverse engineering, Playwright, ClickHouse

## Other locale entry points
- [Russian home markdown](https://ramenm.com/ru/index.md)
- [Simplified Chinese home markdown](https://ramenm.com/zh/index.md)

## Machine-readable access
- Home, chat, and project pages support markdown negotiation when requested with `Accept: text/markdown`.
- Every localized site page also has a URL-based markdown fallback at `/index.md` relative to the HTML page.