-
π I'm currently working on unreal engine and building autonomous AI agents on local hardware
-
π± I'm currently learning tensorflow, C++ and local LLM inference on edge hardware
-
π― I'm looking to collaborate on autonomous AI systems, local LLM pipelines and anyone who likes to share knowledge
-
π€ I'm looking for help with blueprint and Apple Silicon MLX inference optimization
-
π¬ Ask me about unreal engine, ANF β Autonomous Native Forge, Node.js native modules, vLLM on Blackwell, python and everything about IT
-
π« How to reach me turgaysavaci@gmail.com
A cloud-free, self-healing software production pipeline powered by 4 AI agents.
Zero middleware. Zero external dependencies. Pure Node.js native.
PM Agent β Architect Agent β Coder Agent β Reviewer Agent
β__________________________________|
Self-Healing Loop
4 AI agents collaborate to analyze, design, write, and audit code β
running on local hardware with local LLM inference, completely offline.
Currently running on: NVIDIA Blackwell GB10 + DeepSeek-R1-32B
Porting to: Apple Silicon (Unified Memory) Β· ASUS Ascend (NPU)
// What I don't do
const express = require('express'); // β
const axios = require('axios'); // β
const _ = require('lodash'); // β
// What I do
const https = require('https'); // β
const fs = require('fs/promises'); // β
const { EventEmitter } = require('events'); // β
Native Node.js only. If the runtime has it built-in, I don't install a package for it.
This isn't dogma β it's a deliberate choice to understand every layer of the stack.
I don't build in private and launch with a polished demo.
I build in public and document every failure along the way.
Every session produces:
- π΄ What broke and why
- π‘ What was attempted
- π’ What was learned
All of it lives in DEVLOG.md β updated after every session.
