Hi there, I'm Çağrı Giray Keşan 👋

Full-Stack & AI Systems Engineer | React 19, TypeScript, Next.js | Python, FastAPI | Microsoft Open Source Contributor

I architect high-performance client-side web applications, standalone developer tools, and hybrid Retrieval-Augmented Generation (RAG) pipelines with deterministic grounding and AST codebase indexing.

• 🏆 Official Microsoft Open Source Contributor — Contributed production zero-cloud local hybrid RAG recipes to microsoft/PhiCookBook leveraging phi-4-mini and SQLite FTS5.
• 📦 GitHub Developer Program Member — Author of Hybrid RAG Issue & PR Assistant, an official marketplace GitHub Action for deterministic lexical and dense semantic repository triage.
• 🤖 AI Intern @ Microsoft (AI Innovators Summer Program) — Engineered local RAG systems using Microsoft Foundry Local SDK, dense vector embeddings, SQLite FTS5 BM25 hybrid retrieval (RRF), and real-time SSE streaming.
• ⚡ Ex-Frontend Intern @ TurkNet — Developed and optimized production user interfaces handling live customer traffic with React, Next.js, TypeScript, and Redux Toolkit.
• 🧩 Systems Architecture & Performance — Specialized in client-side telemetry, Web Workers concurrency, AST lexing, standalone @vercel/ncc packaging, and on-device SLM inference.
• 🏅 Leadership & Structured Problem Solving — Graduate of McKinsey.org Forward Program (MECE framework & strategic communication) & Global Finalist at Aspire Leaders Program (Harvard-founded).
• 🎓 Education — Web Design & Coding at Istanbul University | Computer Programming Graduate from Istanbul Beykent University (3.61/4.00 GPA).

GitHub Marketplace • Node.js 24 • @vercel/ncc • Okapi BM25 • Dense Vectors • RRF Fusion • Phi-4

• Production-Grade GitHub Action: Automates repository triage using a hybrid RAG pipeline fusing Okapi BM25 keyword scoring with dense semantic embeddings via Reciprocal Rank Fusion ($k=60$).
• Deterministic Line-Span Grounding: Implements markdown AST-aware chunking to output verified citations ([file#L<start>-L<end>]), packaged into a single zero-dependency bundle via @vercel/ncc.
• Official Marketplace Listing: Hybrid RAG Issue & PR Assistant
• Ecosystem Integrations: Native adapters for LangChain, LlamaIndex, Dify, Haystack, and DSPy.

Python • Native OS Events • 15s Debounce • Zero-Conflict Git Guard • Cloud Cron Matrix

• Multi-Repo Auto-Discovery: Monitors My Projects and Open Source Projects (17+ repos) dynamically with zero CPU overhead.
• Autonomous Health & Sync: Auto-detects tech stacks (Node, Python, Rust, Go), executes debounced pre-flight verification, and synchronizes upstream AI cookbooks with automated conflict isolation.
• Cloud Sunday Sentinel: Autonomous cloud cron runner testing framework compatibility every Sunday at 00:00 UTC with automated GitHub Issue alerts.

React 19 • TypeScript 5.8 • Vite 6 • Web Workers • AST Parser • SQLite FTS5 • Vitest • Zero-Cloud

• 100% Client-Side Air-Gapped Cockpit: Developer operating system featuring RepoSense (real-time AST codebase topology at 120 FPS), DevForge (JSON-to-TS/Zod, cURL translator, WASM sandbox), and MindVault (sub-5ms SQLite FTS5 BM25 note search).
• Fault-Tolerant Resilience: Production React 19 Error Boundary architecture, sub-vendor Rollup chunking (17.9 kB main gzip), and 100% automated Vitest unit & benchmark coverage.
• Live Demo: https://cagrik34.github.io/zenith-nexus/

Python • React 18 • TypeScript • FastAPI • Foundry Local SDK • phi-4-mini • SQLite FTS5 • Docker

• 100% Offline Local RAG: Executes phi-4-mini (3.8B) and qwen3-embedding-0.6b (1024-d) locally with zero external API dependency and zero cloud data egress.
• Hybrid Search Engine: Fuses dense embeddings with SQLite FTS5 BM25 using Reciprocal Rank Fusion ($k=60$) with an 89.4% composite quality score across RAG evaluation benchmarks.
• Repository: microsoft-foundry-local-rag-assistant

React 19 • TypeScript 5.8 • Vite 6 • Web Workers • PWA • Client-Side Memory Architecture

• Client-Side Financial Telemetry: High-performance browser terminal computing quantitative metrics across 1,051 TEFAS mutual funds and market benchmarks natively in memory.
• Concurrent Execution: Dedicated Web Workers running Black-Litterman, Monte Carlo, and HRP risk models with 60 FPS Canvas rendering and automated 4-page A4 PDF reporting.
• Live Demo: https://cagrik34.github.io/zenith-atlas/

Python • TensorFlow/Keras • OpenCV • Tkinter • SQLite

• End-to-end computer vision desktop application utilizing dynamic thresholding to classify 13 distinct emotional intensity levels in real time.
• Modular architecture with live Tkinter GUI telemetry and SQLite session data logging for adaptive UI/UX feedback.

• 🦜🔗 langchain-ai/langchain #39965 — Contributed Hybrid RAG Action integration for automated repository triage.
• 🦙 run-llama/llama_index #22853 — Contributed Hybrid RAG Action to LlamaIndex community showcase.
• ⚡ langgenius/dify #41411 — Contributed Hybrid RAG Action to Dify ecosystem tools.
• 🌾 deepset-ai/haystack #12494 — Contributed Haystack Hybrid RAG pipeline component.
• 🎓 stanfordnlp/dspy #10287 — Contributed DSPy Hybrid RAG module to community showcase.

• ⭐ sdras/awesome-actions #915 — Official listing in Sarah Drasner's Awesome Actions catalog.
• 🔍 Danielskry/Awesome-RAG #149 — Added Hybrid RAG Action to Awesome-RAG framework directory.
• 🚀 brandonhimpfen/awesome-github-actions #32 — Added to Awesome GitHub Actions automation tools.
• 📖 coree/awesome-rag #34 — Added to Awesome RAG Tools.
• 💬 GitHub Community Discussion #205923 — Author of technical deep-dive on deterministic BM25 + Dense Semantic Fusion.

• 🏛️ microsoft/PhiCookBook #571 — Merged Official Contributor: Zero-cloud local hybrid RAG recipe with SQLite FTS5 and phi-4-mini.
• 🔷 google-gemini/cookbook #1347 — Zero-cloud local hybrid RAG recipe with SQLite FTS5 and Gemini 2.5/3.7 (google-genai SDK).
• 💎 google-gemma/cookbook #426 — Zero-cloud on-device hybrid RAG recipe with SQLite FTS5 and Gemma 2.
• 🤖 anthropics/claude-cookbooks #847 — Zero-cloud local hybrid RAG recipe with SQLite FTS5 and Claude tool use.
• 🦙 meta-llama/llama-cookbook #1074 — On-device hybrid RAG recipe with SQLite FTS5 for Llama 3.2.
• 🌪️ mistralai/cookbook #399 — Zero-cloud local hybrid RAG recipe with SQLite FTS5 for Mistral AI.
• 🤗 huggingface/cookbook #368 — Zero-cloud local hybrid RAG recipe with SQLite FTS5 and Sentence Transformers.
• 🌿 cohere-ai/cohere-developer-experience #799 — Zero-cloud hybrid RAG recipe with SQLite FTS5 and Cohere Rerank v3.5.
• ▲ vercel/ai #19536 — Next.js SQLite FTS5 local hybrid RAG recipe for Vercel AI SDK.
• 🦙 ollama/ollama-python #721 — Zero-cloud local hybrid RAG recipe with SQLite FTS5 and Ollama embeddings.

• 🌟 Microsoft Türkiye AI Innovators Summer Program (2026) — Selected for hands-on AI architecture & Copilot orchestration.
• 🎓 Aspire Leaders Program (2026) — Global Finalist (Selected among 10,588 finalists from 50,284 worldwide applicants) & Official CEO Recognition.
• 📜 McKinsey.org Forward Program (2026) — 100% Completion (Structured Problem Solving, MECE Framework, Strategic Communication).
• 🌐 Google Developer Groups (GDG) Build With AI Türkiye & HUAWEI Data Science & ML Bootcamp participant.