hyper-ai-cli
v1.1.8
Published
HYPER CLI - Fast, Sharp, Powerful command line interface
Maintainers
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@latestOnce installed, launch HYPER CLI anywhere by running:
hyperRequires 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 RemoteSignedOr 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 bynpm prefix -gis on yourPATH.Another app named
hyper(the Hyper terminal) on your PATH? Usehyper-ai-cliinstead; 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
/copyneeds a clipboard tool:wl-clipboard(Wayland) orxclip/xsel(X11). In WSL it uses Windows'clip.exeautomatically.If
npm install -gfails withEACCES, don't usesudo; 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.
- Official Ollama Model Page: ollama.com/hassanhussain7913/hyper
- Hugging Face Model Hub: huggingface.co/m-hasssssan/hyper-3b-llm
💡 Operating Modes
- 💬 CHAT MODE: Ultra-fast general conversation, reasoning, and synthesis.
- 🎨 IMAGE GENERATION: Synthesizes AI artwork on-the-fly and saves
.pngimages directly to your Desktop (including OneDrive-redirected Desktops on Windows). - ⚡ CODING MODE: High-performance code generation, refactoring, and debugging engine.
🔑 Authentication & 100% Free API Platforms
HYPER CLI supports two 100% free AI providers:
- OpenRouter Free Models: Connect key from openrouter.ai/keys.
- Google Gemini Direct API: Connect key from aistudio.google.com/app/apikey (1,500 free requests/day).
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.
