npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

hyper-ai-cli

v1.1.8

Published

HYPER CLI - Fast, Sharp, Powerful command line interface

Readme

⚡ HYPER CLI — Ultra-Fast Cyberpunk AI Terminal Assistant

High-performance, 100% Free AI streaming CLI engineered for developers with rich cyberpunk visuals, zero-drift terminal menus, and multi-model intelligence.


🚀 Quick Start & Installation

Option 1: Global Installation / Update to Latest Version (Recommended)

Install or update to the latest version on your Mac, Linux, or Windows machine:

npm install -g hyper-ai-cli@latest

Once installed, launch HYPER CLI anywhere by running:

hyper

Requires Node.js 18 or newer (node -v). Works in macOS Terminal/iTerm, Linux terminals, WSL, Windows Terminal, PowerShell and Command Prompt.

🪟 Windows notes

  • PowerShell says "hyper.ps1 cannot be loaded because running scripts is disabled on this system"? Run this once, then open a new terminal:

    Set-ExecutionPolicy -Scope CurrentUser -ExecutionPolicy RemoteSigned

    Or skip PowerShell's script shim entirely by running hyper.cmd, or use Command Prompt.

  • 'hyper' is not recognized? Close and reopen the terminal after installing so it picks up npm's global folder. If it still fails, check that the folder printed by npm prefix -g is on your PATH.

  • Another app named hyper (the Hyper terminal) on your PATH? Use hyper-ai-cli instead; it is the same command.

  • Use Windows Terminal for the best colors, arrow-key menus and emoji. The legacy console works but may show some symbols as boxes.

🐧 Linux notes

  • /copy needs a clipboard tool: wl-clipboard (Wayland) or xclip / xsel (X11). In WSL it uses Windows' clip.exe automatically.

  • If npm install -g fails with EACCES, don't use sudo; point npm at a folder you own:

    npm config set prefix ~/.npm-global && echo 'export PATH="$HOME/.npm-global/bin:$PATH"' >> ~/.bashrc

Option 2: Instant Run Latest Version via npx (No Install Required)

Run the latest version instantly without installing globally:

npx hyper-ai-cli@latest

⚡ Complete Commands Reference Guide

Inside HYPER CLI, type / anytime to pull up the interactive command suggestions box.

| Command | Description | | :--- | :--- | | hyper or npx hyper-ai-cli | Launch the interactive HYPER CLI session | | /mode | Switch operating mode (💬 Chat, 🎨 Image Generation, ⚡ Coding & Dev) | | /model | Switch models (⚡ HYPER-3B Local 6.2GB GGUF, Auto Router, NVIDIA Nemotron 9B, OpenAI GPT-OSS 20B, Cohere North Mini Code) | | /theme | Switch terminal theme (🔴 Red-Shift, 🟢 Matrix, 🟣 Synthwave, ⚪ Obsidian) | | /copy | Copy the last AI response to your system clipboard (macOS, Windows, Linux, WSL) | | /login | Launch authentication wizard to configure OpenRouter or Google Gemini keys | | /logout | Wipe all saved API keys and reset local credentials store | | /history | View persistent conversation memory (last 20 messages) | | /clear | Clear persistent conversation memory | | /effort | Display live developer velocity, line stats, and engine efficiency | | /skills | Display active AI capabilities and synthesis modules | | /plugins | List active workspace extensions | | /system | Print system diagnostics, OS, Node version, and active engine | | /help | Display interactive help manual | | exit | Quit HYPER CLI session |

You can also run these straight from your shell:

| Shell command | Description | | :--- | :--- | | hyper ask "your question" | One-shot question, prints the answer and exits | | hyper auth | Set up or change your API key | | hyper models / hyper mode / hyper theme | Switch model, mode or theme | | hyper history / hyper history clear | View or clear memory | | hyper doctor | Check Node, OS, keys and (for local mode) Ollama | | hyper config | Show the active configuration | | hyper --version | Print the installed version |


⚡ Local AI Engine: HYPER-3B (6.2 GB GGUF)

hyper-ai-cli supports 100% Local Offline Execution using your custom fine-tuned model:

  • Model Engine: hassanhussain7913/hyper
  • Download Size: 6.2 GB (F16 GGUF) / 3.5 GB (Q4_K_M GGUF)
  • Speed: 100+ Tokens / Second (Native C++ Metal/CUDA GPU Acceleration)

🚀 1. IF YOU HAVE OLLAMA:

Don't have it yet? Install it first:

| OS | Install command | | :--- | :--- | | Windows | winget install Ollama.Ollama (or download from ollama.com/download/windows) | | macOS | brew install ollama (or download from ollama.com/download/mac) | | Linux / WSL | curl -fsSL https://ollama.com/install.sh \| sh |

Then run directly in any terminal (PowerShell, Command Prompt, or bash/zsh):

ollama run hassanhussain7913/hyper

🚀 2. WITHOUT OLLAMA (Direct C++ Metal Engine / Python / Hugging Face):

Option A: Direct High-Speed C++ Engine via llama.cpp (No Ollama Required)

Get llama-cli from the llama.cpp releases (Metal on macOS, CUDA/Vulkan/CPU builds for Windows and Linux), or brew install llama.cpp / winget install llama.cpp.

macOS / Linux:

./llama-cli -m hyper-3b-f16.gguf -p "Who created you?"

Windows (PowerShell or Command Prompt):

.\llama-cli.exe -m hyper-3b-f16.gguf -p "Who created you?"

Option B: Python Transformers (Hugging Face Hub)

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "m-hasssssan/hyper-3b-llm"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

Option C: Download Direct GGUF File from Hugging Face

Works the same on Windows, macOS and Linux (pip install -U "huggingface_hub[cli]" first):

hf download m-hasssssan/hyper-3b-llm hyper-3b-f16.gguf --local-dir .

On older huggingface_hub versions the command is huggingface-cli download with the same arguments.



💡 Operating Modes

  1. 💬 CHAT MODE: Ultra-fast general conversation, reasoning, and synthesis.
  2. 🎨 IMAGE GENERATION: Synthesizes AI artwork on-the-fly and saves .png images directly to your Desktop (including OneDrive-redirected Desktops on Windows).
  3. ⚡ CODING MODE: High-performance code generation, refactoring, and debugging engine.

🔑 Authentication & 100% Free API Platforms

HYPER CLI supports two 100% free AI providers:

Run /login inside the terminal prompt anytime to configure or switch your credentials!


🛠️ Development & Local Build

git clone https://github.com/m-hasssssan/hyper-cli.git
cd hyper-cli
npm install
npm run build

📄 License

MIT License. Free and open source for all developers.