Skip to content
View yusufferdogan's full-sized avatar
🏠
Working from home
🏠
Working from home
97 followers · 77 following

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Organizations

@SOFTWARE-ENGINEERING-CSE343

Block or report yusufferdogan

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
yusufferdogan/README.md

Hi πŸ‘‹, I'm Yusuf Erdoğan

πŸš€ Full Stack Engineer (AI & AWS) β€” Serverless β€” Flutter β€” RAG/Agentic Systems

πŸ› οΈ LangGraph β€’ AWS SageMaker β€’ Flutter β€’ LlamaIndex β€’ Next.js

πŸš€ Current Focus

  • πŸ”­ Day job: Full Stack Developer & AI Engineer at WAGMI.Tech
  • πŸ€– Building: Production agentic systems with LangGraph, AWS Bedrock AgentCore, and self-hosted ML
  • ✍️ Writing: Bilingual (TR/EN) AI engineering content on LinkedIn | X @yusufErdoganAI | Substack
  • 🌱 Exploring: LLMOps, agent evaluation, cost-efficient local inference

πŸ” Selected Projects

🧠 wagmiLM β€” End-to-end LangGraph Multi-Agent RAG

Production document summarization pipeline built from scratch β€” infra, model deployment, orchestration, and evaluation

πŸ”§ Stack: Python, LangGraph, AWS SageMaker, Bedrock AgentCore, ChromaDB, Lambda
πŸ“ˆ Results: +34.8% factuality improvement (QAGS: 0.354 β†’ 0.477) over single-agent baseline across 50-query benchmark
Repos: multi-agent-summarization | multisum-agent-agentcore

πŸ€– Clawdbot β€” Production AI Agent with LLMOps

Multi-platform AI agent (Telegram, Discord, CLI) with tool calling, Mem0 memory, and per-request cost observability

πŸ”§ Stack: LangGraph, Python, Mem0, Claude
πŸ’Έ Impact: Reduced LLM costs by 40% through granular token tracking daemon

πŸ”Œ Open Source Claude Code Skills

Published skills for the developer community

πŸ› οΈ Tech Stack

AI & Agentic Systems

LangGraph LlamaIndex Python Hugging Face OpenAI

Cloud & Infra

AWS Docker

Frontend & Mobile

Flutter Next.js TypeScript

Databases

PostgreSQL DynamoDB Redis

πŸ“Š GitHub Analytics

GitHub Stats

GitHub Streak

Top Languages

🀝 Let's Connect

πŸ’‘ "Ship production AI systems. Measure everything. Cut costs ruthlessly."

Popular repositories Loading

  1. STARKREVOKE STARKREVOKE Public

    This Project allows to revoke your ERC20 and ERC721 approvals in Starknet

    JavaScript 10 5

  2. hardhat-foundry-template hardhat-foundry-template Public template

    Forked from foundry-rs/hardhat-foundry-template

    Minimal template to get started with Foundry + Hardhat

    TypeScript 7 1

  3. Formula-Legend-App Formula-Legend-App Public

    https://play.google.com/store/apps/details?id=com.yusuferdogan.FormulaLegend

    Dart 5

  4. Google-Dynamic-Maps-and-Markers Google-Dynamic-Maps-and-Markers Public

    Google Dynamic Maps and Markers

    Dart 5

  5. yusufs-repo yusufs-repo Public

    my c++ projects

    C++ 4

  6. java-Projects java-Projects Public

    my java projects

    HTML 4