Skip to content
View KazKozDev's full-sized avatar

Block or report KazKozDev

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. Markdown is supported. 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
KazKozDev/README.md
banner_slowest



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

  1. 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 144 35

  2. 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 98 21

  3. 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 20 4

  4. cbt-assistant cbt-assistant Public

    Open-source local-first AI mental health chatbot and CBT journal powered by Ollama, with RAG, session memory, mood and sleep tracking, self-assessments, and guided SOS exercises.

    JavaScript 15 1

  5. 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

  6. 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 2