Ramazan Yavuz

Public projects, independent of any business work.

This is my personal hub for open-source projects I publish on github.com/ra-yavuz. Anything here is something I built, found useful, and decided to share. It is not connected to client work or commercial offerings.

For consulting, the broader portfolio, and articles, see ramazan-yavuz.tr.

Stylized illustration of Ramazan Yavuz at a laptop

Projects

hydra-llm

General CLI Linux RAG

Docker for language models, with retrieval baked in. One CLI to download, run, chat with, and search local LLMs. Each model runs in its own container, so docker ps shows what is actually running. Hardware-aware curated GGUF catalog with anonymous Hugging Face downloads (no token required). OpenAI-compatible endpoints on stable local ports. Retrieval-augmented generation is a first-class feature: hydra-llm index ., hydra-llm query "...", hydra-llm chat <model> --rag .. Bake a model, a persona, and a corpus into one alias via hydra-llm create, then chat with it by name. Ships a KDE Plasma 6 panel widget. Pairs with lillycoder for a fully local coding agent. No cloud, no API key, no telemetry.

hydra-llm logo

lillycoder

General CLI Linux

A small chat REPL that drops into any folder. The local LLM on the other end can read, write, and edit your files, run shell commands, and install packages, all gated by per-tool permission prompts and a hard-deny safety classifier. Talks to any OpenAI-compatible /v1 endpoint (llama.cpp, ollama, LM Studio, hydra-llm). No cloud, no telemetry.

lillycoder logo

hydra-rag-hooks

General CLI Linux RAG

apt install. Type rag <q> in Claude Code OR Codex CLI. Done. UserPromptSubmit hooks for both Anthropic's Claude Code and OpenAI's Codex CLI from one apt-installable package. Keyword-triggered local RAG: type rag <q> in either CLI; the hook auto-indexes the project on first use (LanceDB + fastembed, runs fork-detached so your turn is not blocked), then prepends retrieved chunks to the prompt before the model sees it. Both CLIs share the same .hydra-index/ store, the same toggles, and the same bundled MCP server (rag_search, rag_status, rag_list_stores) for model-decided retrieval. apt install wires Claude Code via /etc/claude-code/managed-settings.json; one codex plugin add per user enables Codex. Successor to claude-rag-hook v0.6.x; existing .claude-rag-index/ folders are auto-renamed in place on first run, no re-indexing. Pairs with hydra-llm for shared embedder and store.

hydra-rag-hooks logo

inhibit-charge

Linux CLI

Park your Linux laptop battery at a target charge level using the kernel's inhibit-charge mode. Unlike threshold-only tools (TLP, GNOME, KDE), the battery does not trickle-cycle on AC. No slow drift, no repeated mini-cycles.

inhibit-charge logo

herald

Linux CLI

A small Linux daemon and CLI that prints a daily quote at the top of every new terminal and at login. Cached quote refreshed on a configurable timer (default every 3 hours), local fallback pool, optional user prefix.

herald logo

meowtrics

Linux CLI General

A small animated emoji that lives in your system tray and gossips about your machine. Cat-shaped by default, sweats when the CPU is hot, naps when you're idle. KDE Plasma 6 plasmoid, GNOME / XFCE / Cinnamon / Budgie / MATE / LXQt via StatusNotifierItem, Sway / i3 / polybar via JSON output.

meowtrics logo

Apt repository

Every Debian / Ubuntu tool on this page in one place, kept up to date with the rest of your system. All Debian and Ubuntu packages from these projects (where applicable) are published to a single signed apt archive at ra-yavuz.github.io/apt. Add it to your sources once and every tool installs and upgrades with the normal apt install / apt upgrade commands you already use. New releases land in the repo automatically, GPG-signed, no separate download steps.

One line setup + install

Sets up the signed repo if not already added, refreshes the package index, and installs the package. Idempotent, safe to re-run. Replace <package> with any of inhibit-charge, herald, meowtrics, lillycoder, hydra-llm, claude-rag-hook:

sudo bash -c 'set -e; install -m 0755 -d /etc/apt/keyrings && curl -fsSL https://ra-yavuz.github.io/apt/pubkey.gpg -o /etc/apt/keyrings/ra-yavuz.gpg && echo "deb [signed-by=/etc/apt/keyrings/ra-yavuz.gpg] https://ra-yavuz.github.io/apt stable main" > /etc/apt/sources.list.d/ra-yavuz.list && apt update && apt install -y <package>'

Once the repo is set up, future installs and upgrades are just sudo apt update && sudo apt install <package> and sudo apt upgrade. The sudo apt update step is required: without it apt will not see new packages or new versions.

Tested on Ubuntu (Linux only). The packages should work on any recent Debian / Ubuntu derivative and on WSL2 Ubuntu (it is a Linux distro), with the caveat that projects depending on hardware sysfs (inhibit-charge) or a Linux desktop tray (meowtrics) cannot work inside WSL2 in any meaningful way. macOS support is per-project: hydra-llm runs under Docker Desktop and lillycoder installs from source via pip; the rest are Linux-only by design. Each project page has its own Platform support section.

Why use the apt repository: automatic updates, signed provenance, no manual .deb downloads, plays nicely with the rest of your system. Recommended for any installation you intend to keep.

Alternative, install directly from GitHub: every release attaches a prebuilt .deb to the source repository's GitHub Releases page. Useful for one-off installs, testing a specific version, or environments where adding a third-party apt source is not allowed.

About

Disclaimer

Every project listed here is provided as is, without warranty of any kind. Some projects interact with low-level system interfaces and may affect your hardware. The author is not liable for any damage to hardware, data, or system caused by installing or running these projects. Read each project's README and project page before installing.