Projects | Ramazan Yavuz

Working hub for developers and visitors

ra-yavuz

Project Hub

The hub for all my open-source projects, with install paths, docs, and the signed apt repository.

Visit ra-yavuz.github.io ↗

Agent Talks

Agent workflows

A small local MCP tool for two Codex chats: task handoffs, durable reports, session recovery, and clear turn ownership. Install from source with an agent-readable setup prompt.

Visit Agent Talks ↗

chiron

Developer Tool

A kit for carrying useful coding-agent habits between models. It combines working instructions with hooks for supported Claude Code and Codex CLI versions. The hooks block selected command patterns; they are not a sandbox or a guarantee against bypasses. A small A/B evaluation reports results and limits. Installation instructions are in INSTALL-PROMPT.md.

Visit chiron docs ↗

claude-can-speak

Local AI

Lets Claude Code decide what to say out loud. Most "speak Claude aloud" tools read every reply at you; this one leads with a speak skill that lets Claude voice only what is worth hearing (a "build is done", a heads-up while you look away, a shoutout), while everything else stays text. A speak-everything firehose (its own on/off switch, off by default) is included too, but the deliberate skill is the point. Local neural text-to-speech (Kokoro for natural English, Piper for German, Turkish, and more) runs in Docker, so nothing goes to the cloud. Install with npm install -g claude-can-speak.

Visit claude-can-speak docs ↗

edgecall

Local AI

Route a plain-language request to one of your own functions, using a deliberately weak local model. A small self-hosted, OpenAI-compatible API: you POST a sentence and a tiny model (the kind that runs on a Raspberry Pi or a phone) reads a short paginated menu of your registered functions, picks one, and edgecall runs it and returns the result. The model never sees the whole list at once; it pages through a few options at a time with a "next" choice, so all a weak model has to do is pick one item off a short menu. No embedding model, no index to maintain. Add a function by dropping in a Python file with an id and a one-line description. Talks to any OpenAI-compatible /v1 endpoint.

Visit edgecall docs ↗

local-jev

Local AI

Run a Jev-style typed-decision API locally. local-jev setup creates its own runtime and downloads an open GGUF model. local-jev serve exposes /v1/systemone for yes/no, choice, and score questions. Instead of asking the model to write JSON, local-jev reads the next-token logits for the allowed answer letters and returns structured probabilities.

Visit local-jev docs ↗

doublethink

Security

A publish/subscribe broker with client-side encryption for private channels. The client creates the shared secret locally and registers a derived authentication key. The broker stores encrypted payloads; endpoints and the secret still need protection. ntfy also supports access control, while doublethink adds a different payload-encryption design. Supports optional plaintext public topics, Docker or a native binary, and an Android notification client.

Visit doublethink docs ↗

agent-doublethink

Developer Tool

An MCP server for two coding agents to exchange plans, decisions, and reports over a doublethink channel. Message payloads are encrypted; the broker can still observe channel and traffic metadata. Roles are assigned when a channel is created. Hooks surface partner updates in supported client versions.

Visit agent-doublethink docs ↗

portunus-ovpn

Linux Tool

Native KDE Plasma 6 panel widget for switching OpenVPN connections. Import, edit, remove and toggle .ovpn profiles from the panel; one VPN active at a time by default. Drives NetworkManager and KWallet directly, no second VPN daemon and no third-party PPA. Named after Portunus, the Roman god of keys and gates.

Visit portunus-ovpn docs ↗

vigil

AI Platform

How to build an always-on, autonomous AI operations assistant, and how to keep it diligent. A documentation project: the architecture of a persistent AI operator (per-invocation agent subprocess with a resumable session, supervisor, transport split, channel multiplexers, MCP tools) as a reference design, plus the load-bearing piece most write-ups skip: the doctrine + hooks pattern that re-asserts an engineering standard on every turn so an auto-approved agent keeps verifying before it acts, refuses workarounds, and never claims done without a real run.

Visit vigil docs ↗

hydra-rag-hooks

Local AI

apt install, then type rag <question> in either Claude Code or OpenAI's Codex CLI. UserPromptSubmit hooks for both CLIs from one package. The hook auto-indexes the project on first use, then prepends retrieved chunks from a local LanceDB index before the model sees the prompt. Both CLIs share the same .hydra-index/ store and the same bundled MCP server for model-decided retrieval. Successor to claude-rag-hook.

Visit hydra-rag-hooks docs ↗

lillycoder

Local AI

A local-first coder REPL with file and shell tools. Drop into any folder, bring your own LLM, ship code without leaving the terminal.

View lillycoder on GitHub ↗

hydra-llm

Local AI

Run local LLMs the easy way. Pick a model, download it, chat with it. No cloud, no API key, no telemetry.

Visit hydra-llm docs ↗

hydracoder

Local AI

Enter a project goal and local models plan it, build it, and review it, with no hosted AI in the loop. A dark web UI shows each model as a live terminal. Built on hydra-llm and lillycoder, so it runs entirely on your own hardware.

Visit hydracoder docs ↗

inhibit-charge

Linux Tool

Manages charging around a chosen target on supported Linux laptops. Uses the battery controls exposed by the driver and firmware.

Visit inhibit-charge docs ↗

meowtrics

Linux Tool

Animated tray emoji that gossips about your machine. Sweats when the CPU is hot, naps when you are idle.

Visit meowtrics docs ↗

herald

Linux Tool

A Linux command-line tool with a refresh timer and local quote cache, for new terminals and text logins.

Visit herald docs ↗

tekir

Open Standard

Self-explanatory HTTP responses for AI agents. An RFC 9457 extension that lets a service tell an agent why a request failed and what to try next, in a way the agent can actually parse.

clauding

AI Platform

Autonomous AI dev environment that bundles Claude, Codex, and Gemini into one Docker stack. One command, one workspace, three agents.

Visit clauding docs ↗

sftp2redis-bridge

Integration

Bridge system that ingests files from SFTP into Redis streams for downstream processing.

View on GitHub ↗

leafwallet

Blockchain

A paradigm for accountless crypto wallet generation and ownership. An Ethereum dApp library for wallet-free transaction signing.

View on GitHub ↗