explaingit

sylinko/everywhere

Analysis updated 2026-07-03

5,947C#Audience · generalComplexity · 2/5LicenseSetup · moderate

TLDR

Everywhere is a desktop AI assistant for Windows and macOS you summon with a keyboard shortcut to instantly answer questions about whatever is on your screen, no copy-pasting required.

Mindmap

mindmap
  root((everywhere))
    What It Does
      Screen awareness
      Keyboard shortcut
      Answer questions
      Agent mode
    AI Providers
      OpenAI
      Anthropic Claude
      Google Gemini
      Local via Ollama
    Platforms
      Windows
      macOS
    Use Cases
      Debug errors
      Summarize content
      Rewrite text
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Ask what a terminal error message means and how to fix it without switching away from your current window.

USE CASE 2

Get a plain-English summary of a long article in your browser using a single keyboard shortcut.

USE CASE 3

Rewrite a draft email in a more formal tone by selecting the text and invoking the assistant.

USE CASE 4

Use agent mode to browse the web or run terminal commands to complete a multi-step task hands-free.

What is it built with?

C#.NETAvalonia UI

How does it compare?

sylinko/everywheregerardog/gsudomicrosoft/aspire
Stars5,9475,9515,927
LanguageC#C#C#
Setup difficultymoderateeasymoderate
Complexity2/52/53/5
Audiencegeneraldeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires an API key from OpenAI, Anthropic, Google, or another supported provider to function.

Use freely for any purpose, including commercial use, you must include the original license notice when redistributing.

In plain English

Everywhere is a desktop AI assistant for Windows and macOS that you summon with a keyboard shortcut no matter what you are doing on your computer. When it appears, it can see what is currently on your screen and immediately answer questions about it, summarize it, translate it, or help you rewrite it. The key difference from most AI chat tools is that you do not need to copy text, take a screenshot, or switch applications. You bring the assistant to where your content already is. Practical examples from the README include: you see an error message in a terminal window and ask Everywhere what it means and how to fix it, you are reading a long article in the browser and ask for a short summary, you highlight a foreign word and ask for a translation, you draft a business email and ask for a more formal tone. The assistant reads the context from your screen using accessibility APIs and UI automation, not just a screenshot, which gives it a more precise understanding of what is visible. The application connects to a range of AI providers, including OpenAI, Anthropic Claude, Google Gemini, DeepSeek, and local models via Ollama. You can bring your own API key for any of these or use the project's own cloud service. Beyond answering questions, it has an agent mode where it can browse the web, read and write files, run terminal commands, and call external tools via the MCP (Model Context Protocol) standard. The app is built in C# using the .NET 10 framework and the Avalonia UI library, which is what allows it to run on both Windows and macOS. A Linux version is in progress. The interface uses a frosted glass visual style and supports Markdown rendering and math formula display in responses. The project is available in over ten languages and is licensed under Apache 2.0.

Copy-paste prompts

Prompt 1
How do I set up Everywhere with my own Anthropic Claude API key so I can use it as my screen-aware AI assistant on macOS?
Prompt 2
Show me how to configure Everywhere to use a local Ollama model instead of a cloud API provider.
Prompt 3
I want to use Everywhere's agent mode to automate a workflow that involves reading files and running terminal commands. How do I enable and use it?
Prompt 4
How do I add a custom MCP tool to Everywhere so the AI assistant can call an external service I built?

Frequently asked questions

What is everywhere?

Everywhere is a desktop AI assistant for Windows and macOS you summon with a keyboard shortcut to instantly answer questions about whatever is on your screen, no copy-pasting required.

What language is everywhere written in?

Mainly C#. The stack also includes C#, .NET, Avalonia UI.

What license does everywhere use?

Use freely for any purpose, including commercial use, you must include the original license notice when redistributing.

How hard is everywhere to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is everywhere for?

Mainly general.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Scan in gitsafehub Deploy in gitdeployhub sylinko on gitmyhub

Verify against the repo before relying on details.