rika-agent
Self-hosted Telegram agentic AI with system monitoring, code execution sandboxing, and encrypted key management. Built for privacy-first automation.
Linux-focused developer and ethical security researcher building privacy-respecting tooling, agentic AI systems, and low-level automation workflows.
Self-hosted, privacy-first AI agents that run on your infrastructure with full control and transparency.
The elite, customizable agentic AI system — a persistent, self-hosted assistant that integrates with your shell, file system, and network. Designed for developers who demand control, privacy, and extensibility.
Tools built for control, privacy, and technical depth — from terminal utilities to desktop applications.
Self-hosted Telegram agentic AI with system monitoring, code execution sandboxing, and encrypted key management. Built for privacy-first automation.
Terminal-first AI assistant with both TUI and web-based GUI. Integrates OpenRouter for multi-LLM access. Built for developers who want AI workflows in the terminal or browser.
Polished GTK4 + Libadwaita GUI frontend for yt-dlp. Features per-job controls, concurrent downloads, advanced format/post-processing, subtitle management, and SponsorBlock integration.
Client-side web application for encrypting and hiding files inside images using AES-256-GCM and PBKDF2. All operations occur locally in-browser — no server uploads, no data leakage.
Minimal, cross-platform command-line clipboard utility written in C++. Provides reliable copy-to-clipboard functionality for scripts and terminal workflows without external dependencies.
If my tools have helped you, consider supporting continued development of privacy-first, open-source software.
Principles that guide every tool, system, and workflow I build.
Tools are designed for Unix-like environments first, leveraging native capabilities, POSIX standards, and terminal-centric workflows.
Privacy and system integrity are non-negotiable. Encryption, sandboxing, and minimal attack surfaces are built in from the start.
Focus on low-level understanding: process management, I/O, memory, and networking — not just abstracted frameworks.
User autonomy and transparency take precedence over opaque automation. Every action should be inspectable and reversible.
Open to collaboration on system tooling, security research, and agentic AI projects.