Mert Cobanov
Senior AI engineer building agents with complex memory: backend systems, vector databases, diffusion model training, and generative pipelines. Mostly Python, FastAPI, and Pydantic AI.
Writing about AI engineering, homelabs, and whatever I'm tinkering with
Writing
- Vibe Coding, the Slot Machine and Me Vibe coding hooks the brain with the same addiction mechanism as a slot machine. TR
- KV Cache & Flash Attention LLM inference optimizations, one at a time: a smarter cache, a faster kernel, a better scheduler.
- How AI agent memory works Language models forget the moment they finish replying. Memory is everything the system around them does to make that not matter.
- From latent spaces to JWTs: how agents taught me backend I wrote code every day for years and somehow felt like I wasn't really writing code. Let me explain.
- How I connected my Tesla to Claude I built an MCP server so I could chat with my Tesla. Here's how.
- See all 9 posts
Projects
-
Ollaya
Ollama for decision models: pull and serve Laya, decider, NLI and GLiClass locally behind a TypeSafe-compatible API.
ollaya.dev
-
PS5LM
llama.cpp on a jailbroken PlayStation 5. Open language models run on the console's own CPU, and you chat with them in its browser.
ps5lm.cobanov.dev
-
herdrchat
Control your coding agents from your phone, on iOS and Android.
herdrchat.cobanov.dev
-
Ahead
A bilingual daily briefing that turns the AI and technology news cycle into a sourced five-minute morning read.
ahead.cobanov.dev
-
Dantel
Crochet lace for your Mac. Drag to fold, blur your screen, and make it yours. On the Mac App Store.
dantel.cobanov.dev
-
terminal.army
A multiplayer space strategy game you play from your terminal.
terminal.army
-
PocketVibe
A launcher and game store for ROCKNIX and Android handhelds, full of three.js games made with AI coding tools.
pocketvibe.dev
-
ghbar
Pull requests and issues from your repositories, in the macOS menu bar.
ghbar.cobanov.dev
Libraries
-
Semantic text clustering using sentence embeddings and agglomerative clustering.
-
Aspect ratio bucketing for diffusion model training. PyTorch native, DDP correct.
-
Unsupervised image clustering with modern deep embeddings, PCA and K-Means.
-
Convert depth map images to RGB normal maps for shading and 3D workflows.
-
Summarize web pages and YouTube videos with pluggable LLM backends.
-
Realtime webcam streaming and video processing with a FastAPI UI.
Contact
Based in Los Angeles. Open to interesting projects, collaborations, and long emails about AI, art, and tooling.