Projects, guides and writing on AI coding workflows and developer tools, most of them built with AI coding agents such as Claude Code and Codex. Every entry passes a script check and a manual review before it is listed. My profile is on GitHub (opens in a new tab).
Start here
Registry · AI coding agents
A registry of reusable operating loops for AI coding agents such as Claude Code, Codex, Cursor and Hermes. Each loop names its trigger, its proof and its stopping condition, and CI validates every entry against a schema.
Licence: MIT
Visual guide · English + Turkish
A static guide to operating Hermes Agent from the terminal: setup, memory and skills, the messaging gateway and scheduled jobs. Commands were checked against Hermes Agent v0.21.5. Unofficial; not affiliated with Nous Research.
WebGL2 app · browser + desktop
Turns a camera, a screen, a video or a song into live ASCII, dither, halftone, braille or pixel art. Runs in the browser, with desktop builds for macOS, Windows and Linux.
Built in one night by one person directing five AI coding agents, with a review step and CI.
Prompt framework + A/B harness
Restructures a prompt into 8 layers and ships a blind A/B harness that compares it with the raw prompt. In my own pilot (50 pairs, 2 Gemini models) the amplified prompts were preferred in 19.6% of decided pairs, so they lost.
Learning cards · English + Turkish
A set of 81 prompting and learning cards with 243 worked scenarios. The examples are teaching material, not benchmark results.
Licence: CC-BY-4.0
Live agent map · TypeScript, three.js, Bun, Python
A live map of the AI coding agents running on one Mac. When an agent stops to ask a question or to ask for permission, its unit turns red, an alarm line runs to the operator and a counter shows how long it has waited.
Status: prototype, closed source. The rendering engine is Giacomo Magnanini's pdoom-video (MIT), via Luis Bizarro's evangelion adaptation (MIT); CITADEL adds the map, the live data path and the alarms.
17 entries
Showing 17 of 17 entries
AI coding & agents
A deterministic, model-free simulator of a finite authority model for AI agents: agents get narrow, scoped authority and return evidence, and a separate trusted layer decides what becomes canonical state.
A simulator proof, not a production agent runtime. The full property proof is not established yet, and the README lists what is still missing.
AI coding & agents
A registry of reusable operating loops for AI coding agents such as Claude Code, Codex, Cursor and Hermes. Each loop names its trigger, its proof and its stopping condition, and CI validates every entry against a schema.
AI coding & agents
A command-line tool that reads the local Claude Code session logs and shows token use and estimated cost per session.
Last verified 2026-10-06 against Claude Code 2.1.291. Not actively maintained; the cost figure is a rough estimate.
AI coding & agents
A live map of the AI coding agents running on one Mac. When an agent stops to ask a question or to ask for permission, its unit turns red, an alarm line runs to the operator and a counter shows how long it has waited.
Developer tools
Answers questions about your own documents with citations back to the source, using NotebookLM through the unofficial notebooklm-py library. It needs a logged-in Google account.
Creative coding & WebGL
Turns a camera, a screen, a video or a song into live ASCII, dither, halftone, braille or pixel art. Runs in the browser, with desktop builds for macOS, Windows and Linux.
Guides & learning
A static guide to operating Hermes Agent from the terminal: setup, memory and skills, the messaging gateway and scheduled jobs. Commands were checked against Hermes Agent v0.21.5. Unofficial; not affiliated with Nous Research.
Creative coding & WebGL
A browser visualizer that draws fractal patterns with WebGL2 fragment shaders and feeds each frame back into the next.
First version generated in Google AI Studio from one structured prompt, then fixed in follow-up sessions. No tests; frame rate not measured.
Writing & research
The build story of Glyphbooth: the plan, the rule that made subagents write the code, and what screenshots, tests, review and CI caught.
Creative coding & WebGL
A browser instrument with four bounded physics and biology scenes (PELAGIC, STRATA, ORBIT, CHORUS) drawn on one Canvas 2D surface. Pointer and touch input perturb each scene, and the system settles when released.
Release 1 only. Static site with no backend, accounts or analytics.
Guides & learning
A set of 81 prompting and learning cards with 243 worked scenarios. The examples are teaching material, not benchmark results.
Creative coding & WebGL
A prompt machine with no language model inside. It turns a number into a build dare for a frontier model, and keeps an honest wall of the runs.
Every sentence traces back to a gene and an atlas entry, and the same number always gives the same prompt. The wall holds one card so far: the machine's own build.
AI coding & agents
Restructures a prompt into 8 layers and ships a blind A/B harness that compares it with the raw prompt. In my own pilot (50 pairs, 2 Gemini models) the amplified prompts were preferred in 19.6% of decided pairs, so they lost.
Case studies
A mechanical keyboard comparison and buying-guide site that earns Amazon affiliate commission. I run the product catalog, write the articles and keep an evidence ledger for every claim; the storefront runs on a managed platform (UseBravery).
Repository is private. The product is keyboard research, not AI work.
Developer tools
A read-only macOS script that reports the USB-C speed and power signals macOS has negotiated for the current cable, port and device. It does not certify or benchmark cables.
Systems & hardware
Unofficial Rust bindings for the Cactus on-device inference engine: chat, streaming, embeddings and speech-to-text. Distributed from GitHub, not crates.io.
Systems & hardware
A gateway written in Rust that reads Modbus TCP and RTU devices and publishes the values over a REST API, WebSocket, MQTT and Prometheus metrics.
Not tested against real PLCs or serial hardware; throughput not measured. There is no live demo. MQTT TLS is not implemented.
Other people's repositories
Merged pull requests only.
Merged 28 Sep 2026
dmtrKovalenko/fframes #150 (opens in a new tab): Update the README for 1.0 and agent workflows
Merged 24 Mar 2026
glitch-rabin/swarma #1 (opens in a new tab): Fix the MCP stdio transport: prevent stdout corruption and a pipe crash
Merged 29 Dec 2025
cactus-compute/cactus #270 (opens in a new tab): Add the Rust SDK (cactus-rs) to the community bindings list
Upstream later added its own Rust bindings: a raw FFI crate in February 2026 (#382) and bindings/rust in May 2026 (#653).
The gate
An entry is listed only when it passes all of these:
A script checks rules 1 to 4 and the GitHub star counts on every change to this site and again after every deploy. I check the other numbers and the screenshots by hand.