Skip to content
View Tahsine's full-sized avatar
🏠
Working from home
🏠
Working from home

Block or report Tahsine

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.

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
Tahsine/README.md

Hey, I'm Tahsine

AI Engineer building agentic systems and LLM applications. Remote · Benin

I design AI assistants, RAG pipelines, and production-ready AI products — from zero-dependency SDKs to offline-first mobile apps.

  • 🔭 I'm currently exploring multimodal AI agents and offline-first architectures
  • 🌱 I'm diving deeper into on-device LLMs and real-time voice agents
  • 💬 Ask me about RAG, agentic workflows, or running LLMs on free GPUs
  • 📫 Reach me at borrelle.dev@gmail.com
  • 😄 Pronouns: KalineZephyr
  • ⚡ Fun fact: I built a 35B LLM server on free Kaggle GPUs — no paid cloud required

Tech Stack

Python · TypeScript · PyTorch · LangChain · LangGraph · FastAPI React Native · Streamlit · llama.cpp · Docker

Featured Projects

zeroagent — Agent SDK in pure Python...

kaggle-llm-server — Free 35B...

oh-matilda — Offline-first RAG...

Connect

Portfolio · LinkedIn · Blog · Email


Je parle et code aussi en français.

Pinned Loading

  1. kaggle-llm-server kaggle-llm-server Public

    Run a free 35B multimodal LLM on Kaggle GPU — accessible from any OpenAI-compatible client

    Jupyter Notebook 3 4

  2. oh-matilda oh-matilda Public

    Agentic & Offline First — RAG assistant with local LLM, document search, and multi-language support

    TypeScript 2 1

  3. zeroagent zeroagent Public

    Agent IA + Workflow SDK en Python pur. Zéro dépendance externe. CLI ReAct avec tool calling, streaming, et chat. 🦦

    Python 1