Havuz

fauxnix, AI agent’ların Linux tarzı shell komutlarını Windows’ta PowerShell üzerinden çalıştırmasını sağlayan bir çeviri katmanıdır.

Neden yükseliyor · AI agent’ların shell kullanımı yaygınlaşırken Windows ile bash arasındaki uyumsuzluğu hedefliyor; README’de 109 çevrilen komut, 400’den fazla otomatik test ve GNU coreutils ile karşılaştırılan 253 test vakası bildiriliyor. 49 günde 697 yıldız dikkat çekici ilgiye işaret ediyor, ancak son 28 günlük commit ve farklı yazar verileri ölçülmediğinden geliştirme temposu hakkında çıkarım yapılamaz. Benchmark sonuçları proje tarafından yayımlandığından bağımsız doğrulama olarak değerlendirilmemeli.

Mirage, AI agents için farklı veri kaynaklarını, sanal CLI araçlarını ve çalışma ortamlarını ortak bir terminal arayüzünde birleştiriyor.

Neden yükseliyor · 144 günlük yaşına karşılık 3663 yıldız ve son 28 günde 1207 commit dikkat çekici ilgi ve geliştirme temposuna işaret ediyor. Ancak bu dönemdeki farklı yazar sayısı 4; yüksek commit sayısı geniş katkıcı tabanının kanıtı değil ve README dışında bağımsız benimsenme verisi verilmemiş.

Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no

Sync AI context across every terminal window. 3 seconds to know what to work on next.

Claude Code statusline and rate limit tracker with pace-aware quota monitoring. Pure Bash + jq, single file.

A customizable terminal splash screen with plugin-based data sources.

Markdown-first orchestration for 71 specialists across Codex, Claude, Gemini, and Grok. Chrono coordinates scoped tasks in isolated git work

Multi-agent autonomous framework — let your AI work while you sleep 🌙

Clear your terminal with a crackling wall of ASCII flames.

AI-native bash for humans and AI agents: real bash syntax, real Unix commands (winuxcmd), real git via niu-git. Native Windows/Linux/macOS -

Named CODEX_HOME profiles and ChatGPT Desktop windows with separate local state, without copying tokens

Run multiple AI coding accounts at the same time.

A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script/JS/Swift). Security

macOS companion toolkit for power users

A memory layer for Claude Code that learns as you work. Persistent, per-context memory as plain markdown in your own git repo. No server, no

Linux 一键巡检脚本，纯 Bash 单文件，跨 30+ 发行版（RHEL/Debian/SUSE/Alpine/Arch 等），自动检测系统、性能、安全、网络、服务共 60+ 项，输出工程师可读的 HTML 报告。

Claude Code hooks that auto-switch model tier based on task complexity

Your media stack, automated

A configurable Bash/PowerShell loop that runs an AI coding CLI with a fresh session each iteration

🕹️Arcade-themed statusline for Claude Code — Pac-Man inspired chase game & Pikmin Bloom inspired flower trail

Use Bitwarden to manage your global shell environment secrets.

Universal academic document & thesis engine for AI agents and engineers.

Undo mv, rm, cp and more from your shell. Journaled to SQLite, deletions go to the trash, nothing gets lost.

Autonomous AI Company OS — 14 AI agents loop 24/7, ship real software

Beginner-friendly guide and scripts for deploying projects with Git, focused on practical Shell-based workflows, basic automation, and simpl

Generative rocket greeting for a bash, zsh, fish, and PowerShell — every new terminal spawns a unique, deterministic artwork

A Claude Code skill that bridges Claude Code to the Codex CLI: externalizes plan, files, conversation and conventions into an on-disk bundle

IDE-style inline autocomplete for your macOS terminal — an open-source, Fig-style completion engine for zsh, bash & fish.

🔊 Hear how developers actually pronounce kubectl, nginx, GIF & 1,900+ tech terms. Sourced dictionary + CLI + VS Code + GitHub Action + MCP +

Pre-login warning banner and dynamic post-login MOTD for Linux — standalone shell installer and SaltStack formula from one unified schema.

Time gated git commit blocking hook. "Helps you stay focused on what you should be doing at certain times of day". Especially if you're a pu

Autonomous multi-agent orchestration engine for software repos — L0/L1/L2 agents, leases, gates, audits, git-worktree isolation. Detached di

Right-click any file in Finder → AI gives it a meaningful name. Images, videos, PDFs, Word, Markdown, folders. macOS native, BYOK Gemini, MI

Git worktrees that set themselves up. One shell function, zero fluff.

Auto-generate Conventional Commits from your staged diff — detects scope, type, and context. Cross-platform (Windows/Linux/macOS). No depend

Use Claude Code's UI with OpenAI GPT-5.6 (Sol/Terra/Luna) as the engine — powered by your ChatGPT Plus/Pro subscription via a local Codex pr

Pure bash CLI tool for Proxmox VE 7.x/8.x/9.x clusters management. No Python. No Go. No SDKs.

See your AI coding costs in real time. Tokenline adds context usage, prompt-cache savings, TTL countdown and rate-limit pacing to Claude Cod

Workspace for Markdown, MDX, JSON, YAML, shell scripts, and text files.

Lightweight SSH login observability for Linux servers. Sends a rich push notification via ntfy on every SSH login and failed attempt, and sh

AI-powered terminal workspace manager (tmux + Claude Code)

A minimalist tmux session manager & fuzzy switcher powered by fzf. Launch named zoxide/fd sessions from a cold shell, jump to panes, search

Simple deployment tool to deploy your Hermes Agent to Cloud

Semantic shell command safety classifier — AST-based risk scoring for AI coding agents

Beginner-friendly nginx setup and virtual host manager for Linux. One installer, one easynginx command. Reverse proxies, SSL via Let's Encry

AI agents the Unix way

🏳️‍🌈 turn your zsh/bash/fish shell prompt into ❤️🧡🤍🩷💜 lesbian flag colors!!! 🏳️‍⚧️

Shared console MCP server for any shell (bash, pwsh, cmd) — AI and user work in the same terminal. Real-time command visibility, interactive

Stop opening /usage — a Claude Code status line that does the weekly-limit math: today's share, sustainable burn rate, sleep-aware pacing. P

The honest macOS tune-up — diagnoses what's actually slow, fixes only what's safe & reversible, scores your Mac 0-100. One bash script, zero