Skip to content
Atlas profile

Yahya Efe Kuruçay

@efekurucayVerified GitHub profile

AI Product Engineer · Founder @AkdenizOS · CS @akdenizcse

AI-Atlas score

Specialist
0100
Strongest
AI Agents
75.5/100 domain score
Rank
2nd=
of 71
Türkiye
1st
of 2
  • TürkiyeLocation
  • 12 Nov 2026Mapped
  • 19 / 41AI projects
01Skills matrix

AI Skills Matrix

AI Skills Matrix scores, 0 to 100
Machine Learning67
Computer Vision50
Data Science34
NLP & LLMs74
AI Agents76
MLOps24

Each node is one domain, scored only from evidence in these public repositories. Select one to see why.

Deep, repeated, well-engineered work in this domain.

02Evaluated projects6 of 19

41 public repositories → 19 with AI work, evaluated. The other 22 (repositories without AI code, forks and empty repositories) are not scored and have no effect on the result. How repositories are selected

Ranked by contribution

Ordered by how much each project adds to the Atlas score, not by its own score. A project with evidence in several domains can rank above one with a slightly higher project score. Choose a domain to focus on the projects with meaningful evidence there.

01
72.1

Advanced

27% of Atlas Score

Agent System· Python

Immortal Agent is an autonomous AI agent designed to stay alive by cycling through LLM providers, self-repairing by generating new wrappers when all known providers fail, and featuring health-based routing, circuit breaking, and persistent memory.

AI Agents0.95NLP & LLMs0.90MLOps0.30Machine Learning0.20
ai-agentautonomous-agentcircuit-breakergroqllm
02
59.1

Advanced

22% of Atlas Score

ML Application· Swift

RLeon — illustrative UI preview (Speech, Vision OCR, Ollama)

RLeon is a macOS application that integrates on-device speech recognition, Vision-based OCR, and local LLMs via Ollama with a tool calling system to enable voice-driven dictation, screen text extraction, and automated macOS actions.

Machine Learning0.90NLP & LLMs0.90Computer Vision0.70AI Agents0.50
computer-visionllmlocal-firstmacosollama
03
60.1

Advanced

9% of Atlas Score

Library / Framework· TypeScript

The Model Subsession Protocol is a TypeScript library that provides a framework for managing nested sub-sessions in LLM chat interfaces to reduce context bloat. It includes a protocol specification, reference implementation with session and subsession management, context merging policies, and unit tests.

NLP & LLMs0.90Machine Learning0.70MLOps0.30AI Agents0.20
04
61.0

Advanced

7% of Atlas Score

AI Developer Tool· JavaScript

gitdex is a CLI tool that converts a local codebase into structured text bundles optimized for LLM consumption. It filters noise, compresses content, splits large files safely at top-level boundaries, and generates an index for easy navigation.

NLP & LLMs0.90Data Science0.20
05
57.4

Implementation

7% of Atlas Score

Agent System· JavaScript

docentic is a self-hosted, embeddable agentic assistant for static sites that crawls site content, stores it in SQLite with FTS5, and uses a language model with a tool‑calling loop to answer visitor questions.

NLP & LLMs0.80AI Agents0.70Data Science0.50Machine Learning0.40
06
53.5

Implementation

6% of Atlas Score

Library / Framework· Python

agent-write-apis is a Python library and command-line tool that provides a unified interface to publish content to various public, no-auth HTTP endpoints (paste services, file upload services, notification services, etc.). It enables AI agents and other applications to easily share output, store data, and send alerts without requiring API keys or handling service-specific details.

AI Agents1.00