Havuz

Vendor-neutral Go CLI for the Open Knowledge Format. Create, validate, lint, index, search, and graph OKF bundles. Built to be driven by AI

Generate project-tailored AI assistant rules & skills (CLAUDE.md, .cursorrules, Copilot instructions, AGENTS.md) in under two minutes. Works

SSH port-forwarding manager with a TUI — toggle local, remote and SOCKS5 tunnels from one screen. Single Go binary, background daemon, autos

Terminal UI for monitoring localhost processes and ports. Real-time CPU/Memory graphs, process management. Built with love & Rust.

High-performance Rust token compression engine for LLM inputs. Plugin-based, 50–95% token savings, AI-export diagnostics, CLI / Server / IDE

Kibana's DevTools in a terminal: query Elasticsearch or OpenSearch when Kibana isn't there, or is down. One Go binary for Linux, Windows and

Local-first Python CLI for safer log sharing: redact secrets, tokens, emails, and local paths before posting to GitHub issues, tickets, or A

contextzip CLI: zip the right parts of your codebase for ChatGPT, Claude or Gemini, then apply the AI’s changes back. Skips dependencies, re

Compare design directions inside existing apps. Try many variations of a component, feature, page or user-flow quickly. Try all your ideas.

AI launch-video generator — films your real web app with a cinematic camera, motion blur, and music. A CLI alternative to Screen Studio for

🔒 Jail OpenCode, Claude Code, Copilot CLI and OmO in micro-VMs: only your project folders, only the networks you allow.

OSS license watchdog. Monitors GitHub repos you depend on and alerts you when a license changes, explaining exactly what you can no longer d

MCP server for Claude Desktop and other Model Context Protocol clients — sandboxed filesystem access (read/write/edit/search) plus Dev Mode-

Git repository activity at a glance. Contributors, heatmap, trends, branch comparison and changelog. Zero dependencies.

npkill for Next.js — nuke bloated .next folders and reinstall a fresh instance. Monorepo & pnpm aware.

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

The engineering trust layer for AI-generated code — independent review, evidence, and acceptance after your AI coding tool writes the code

Back up your dev environment — language runtimes & global CLI tools — and restore it on a new machine. Backups live in your own GitHub repo.

Terminal UI for Tilt.dev, inspired by lazygit

Structured file edits for AI agents (JSON/YAML/TOML, markdown, AST, dry-run, MCP). Not a generic filesystem MCP.

Remove Claude/AI attribution from a GitHub repo in one command clean commit history, force-push, and refresh the Contributors graph so @clau

The skill composer for AI agents — merge skills from Anthropic, OpenAI, GitHub Copilot, Microsoft, Google + 8 more ecosystems with AI-powere

Your localhost, accessible from anywhere. Simple, secure, and open source.

Find gaps between .env, .env.example, shell variables, and Python code.

A docker compose for Apple's native container runtime — run your compose.yaml on Apple silicon, no Docker daemon.

A Git-native dependency admission controller. Evaluates trust signals on every dependency change and blocks commits or builds when packages

One-command Cloudflare Tunnel Zero Trust CLI

A coding agent that lives in your terminal. Local Ollama first, or hosted models through the Aether AI fleet.

Fix the Google Antigravity 2.0 bug that splits one project into duplicate numbered Projects-panel entries (MyApp, MyApp 2, MyApp 3...). Scan

Claude Code plugin for visual docs — annotated screenshots, feature demos, flow walkthrough recordings (gif/mp4), terminal captures and befo

An AI-powered Git pre-commit/pre-push security gate

The Search Engineer's Toolkit — open source CLI tools for Elasticsearch, OpenSearch

Static security & correctness linter for Payload CMS. Zero-config, deterministic, ts-morph-based. Catches access-control gaps, unsafe Local

Go LLM Execution Model — Go 原生 AI 编程 Agent CLI。单二进制、三层记忆、YAML 权限规则，TUI 对齐 Claude Code / Codex。