KazKozDev

Follow

Artem KK KazKozDev

Follow

Making LLMs do what they're told

44 followers · 10 following

Achievements

Achievements

KazKozDev/README.md

Applied AI Developer working on open-source LLM applications.

Agents & tool calling — MCP servers, multi-step agents with structured outputs, retries, and guardrails
RAG — chunking, hybrid retrieval, re-ranking, grounded citations, eval-driven iteration
Local & cloud inference — Ollama and vLLM alongside OpenAI / Anthropic
Production — Python, FastAPI, Docker; tracing, evals, and cost/latency monitoring built into every project

Python · TypeScript · MCP · Ollama · RAG · Fine-tuning · Tool Calling · Structured Outputs · LLM Evaluation

Pinned Loading

NovelGenerator NovelGenerator Public

Local AI novel generator for Gemini and Ollama. Write coherent novels chapter by chapter with causal planning, persistent story memory, scene handoffs, and continuity checks.

TypeScript 152 36
book-translator book-translator Public

Offline AI book translator for EPUB, PDF, and TXT. Translate entire books and novels locally with Ollama, document glossaries, refinement, and side-by-side review.

Python 110 21
auto-vertical-reframe auto-vertical-reframe Public

Scene-aware vertical auto-reframe CLI that turns horizontal footage into 9:16 video without losing the subject.

Python 21 4
prompt-playoff prompt-playoff Public

Prompt optimization and benchmarking for local LLMs: picks the right prompt technique for your task and measures it on Ollama. DSPy-compatible.

Python 2
WebOperator WebOperator Public

Local-first AI browser agent and MCP server for Chrome — runs on Ollama or any cloud model. Open-source alternative to OpenAI Operator.

TypeScript 3
docket docket Public

Invoice and receipt OCR for Python: extract cited, validated data with local or hosted LLMs

Python 1