Projects

Release engineering CLI — single static binary, zero runtime dependencies, fully configurable. Automated semantic versioning from conventional commits.

Cross-platform dotfiles managed by Chezmoi with Homebrew/apt and per-language version managers. One-command bootstrap for macOS and Linux with Neovim, Tmux, Zsh, and AI agent skills.

Fast OpenAPI 3.x code generator for TypeScript, React/SWR, and FastAPI — zero runtime deps, first-class SSE streaming

saige — Super Artificial Intelligence Graph Environment. A unified Go SDK and CLI for streaming AI agents, knowledge graphs, and RAG pipelines.

AI-native smart home skill — lets AI agents control Zigbee devices directly, no cloud, no hub.

Communication-focused language guides built from markdown — scenario-based PDFs with full Unicode/CJK support.

Generative Artifact Protocol (GAP) — an open standard for token-efficient artifact updates and streaming. Rust apply engine + eval CLI.

AI-powered GitHub profile metrics — SVG visualizations, project classification, and README generation. CLI, npm package, and GitHub Action.

Universal agent skill and sub-agent manager with TUI

Embed source files into any text file using comment markers — CLI, crate, and GitHub Action.

Capture showcase screenshots and GIFs from web apps, desktop, and terminal. Single Rust binary, no runtime deps.

A production-grade Rust framework for Linear Genetic Programming research, featuring modular architecture, Q-Learning integration, automated hyperparameter optimization, and support for reinforcement learning and classification tasks.

An open ecosystem for tool-agnostic AI agent memory

Voice-driven coding for Neovim. Speak your intent, edits appear in your editor.

Type-safe async pipeline framework for data processing in Rust

Here begins the new career. A template-driven CLI that transforms structured resume data into polished PDFs, DOCX, HTML, LaTeX, and Markdown — with pluggable templates and multi-agent AI assessment.

Connect your ideas, privately. Privacy-first AI research agent with a persistent knowledge graph — all inference runs locally.