👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.

The setup I use for pi. Changes a ton, don't recommend hard copying it, just a taste of what's possible with it

Codebase intelligence for TypeScript and JavaScript. Free static layer: unused code, duplication, circular deps, complexity hotspots, architecture boundaries. Optional paid runtime layer: hot-path …

Easy self-hosting for Docker-based web apps

Interactive architecture diagrams for codebases

Generate code from the terminal!

Comparison between open source PI agent and closed source Claude Code agent

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

Official specification for Token-Oriented Object Notation (TOON)

A curated list of awesome Marko modules, plugins and resources

🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sa…

Minimal self-hosted markdown editor with inline comment threads

AI Workspace - Give your AI agents memory that spans across projects.

Wrap Gemini CLI, Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.5, Grok 4.3, Claud…

Open-source BrowserAct + n8n workflow library for web automation. Free, community-driven workflows for data scraping, monitoring & e-commerce.

Mirror repository, PRs are not watched, please use Xfce's GitLab

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Autonomous Kanban board where AI agents plan, implement, and review your tasks — fully hands-off.

Awesome Security lists for SOC/CERT/CTI

Учебный проект для демонстрации реализации Event-Driven Design и Domain-Driven Design в модульной архитектуре

Material Design 3(Material You) UI components using Web Components.

Validate, lint, and assert correctness of LLM-generated outputs. Like ESLint for AI.

Specs first. Code second. Proof always. You define the what. LLMs generate the how. hlv validates the proof.

TextUI frontend for php-code-coverage

X-Apps [Text] Editor (Cross-DE, backward-compatible, GTK3, traditional UI)