MudrikNow — Open-Source

press alt + space — it sees your screen

Stop explaining your screen to AI.
Your AI sees what you see.

MudrikNow is an open-source desktop AI agent that sees what you see — and answers, acts, or guides you step-by-step through any task.

Desktop · MIT License · v3.3.0

Why MudrikNow

Three promises.

01

AccessInstant Access

Show MudrikNow instantly with a shortcut, whenever you need it.

02

ContextLess Context

It understands what's on your screen, so you explain less.

03

ReachAny Task. Any Window.

Get help and guidance through any task and any window.

Demo

See it in action.

Bring your own model

AnthropicOpenAIGoogleGroqDeepSeekOllamaZ.AIOpenRouterKimi AnthropicOpenAIGoogleGroqDeepSeekOllamaZ.AIOpenRouterKimi

How it works

Install in four steps.

From zero to an AI that sees your screen in about two minutes.

01

Install Node.js ≥ 20

The runtime MudrikNow depends on. Get the LTS installer.

nodejs.org →
02

Install the AI runtime

One global npm package. Open PowerShell and run:

$npm i -g opencode-ai
03

Run the MudrikNow installer

Download the installer and double-click.

MudrikNow 3.3.0 installer (.exe) →
04

Add your AI model

Open ⚙ Settings → API Keys → paste a provider key (Anthropic, OpenAI, Google, Kimi, DeepSeek…), then pick a model. A multimodal (vision) model is recommended — MudrikNow auto-screenshots every activation; Google Gemini Flash-Lite is a great free pick. Or authenticate via CLI:

$opencode auth login

First launch triggers Windows SmartScreen — More info → Run anyway.

What it does

Six ways MudrikNow goes beyond chat.

01

VisionSees any app

Reads the full UI tree — buttons, fields, text, menus — through native accessibility (UI Automation). A full-screen screenshot with a coordinate grid is captured on every activation.

02

SandboxedClosed by default

Read-only shell for diagnostics (writes, deletes, piping blocked — violations kill the session). No filesystem writes. The model runs in a sandbox with an allow-listed capability surface.

03

GuideAuto-Guide

MudrikNow walks you step-by-step through multi-step tasks. An owl cursor points to each target with instructions in a speech bubble.

04

ChatQuick chat

Press Alt+X — the panel opens instantly without scanning your screen. Always one keystroke away.

05

ModelsBring your own model

Anthropic, OpenAI, Google, Groq, DeepSeek, Ollama, Z.AI, OpenRouter — paste your key in the settings panel. No terminal auth dance. Multimodal (vision) models recommended — MudrikNow auto-screenshots every activation; Google Gemini Flash-Lite is a great free pick.

06

DemoSee it in 10 seconds

One hotkey. MudrikNow reads your screen, answers, and acts — no copy-pasting.

▶ Watch the demo

Hotkeys

Press a key, get help.

Alt+Space

Reads your active window's full UI and anchors on what you're pointing at. MudrikNow opens on the opposite side of your screen, ready to help.

Alt+X

Quick chat — opens the panel instantly without capturing context. For questions that don't need screen awareness.

Esc

Cancel: stops streaming or closes the panel.

Enter

Send — Shift+Enter for a newline.

All hotkeys are rebindable from the menu.

Privacy & security

Sandbox first.

Shell is read-only-only (mutation/piping blocked — violations kill the session); filesystem writes are off. UIA actions are allow-listed. A full-screen screenshot with a coordinate grid is captured on every Alt+Space (and via the Capture Context button) — the AI sees the pixels as well as the UI tree.

Read the full threat model in SECURITY.md →
Shell / PowerShell execRead-only only
Filesystem writeOff
Windows UI AutomationAllow-listed
Filesystem readWorking dir only
Screen pixelsAuto on every Alt+Space

About

Hi, I'm Abdullah Magdy.

A dev who got tired of explaining context to AI chats — so I built MudrikNow on nights and weekends. It's open source; contributions and ideas are welcome 🤝

Let the owl see your screen.

Open-source, sandboxed, and one hotkey away. Download MudrikNow and stop explaining your screen to AI.

↓ Download