# Snippy: An Open-Source GPT-4 Screen-Sharing Assistant Built with Tauri and Rust

DevFeed: [Snippy: An Open-Source GPT-4 Screen-Sharing Assistant Built with Tauri and Rust](<https://devfeed.tech/articles/snippy-an-ai-assistant-with-eyes-39726.md>)

Original publisher: [Read original article](<https://www.timdbg.com/posts/snippy-assistant-with-eyes/>)

Author: Tim Misiak

Published: 2024-04-21T17:47:33Z

Content type: tutorial

Language: en

Sources: [TimDbg](<https://devfeed.tech/sources/timdbg.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [screen](<https://devfeed.tech/topics/screen.md>), [Tauri](<https://devfeed.tech/topics/tauri.md>), [Rust](<https://devfeed.tech/topics/rust.md>), [screenshot](<https://devfeed.tech/topics/screenshot.md>), [cross-platform](<https://devfeed.tech/topics/cross-platform.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [API keys](<https://devfeed.tech/topics/api-keys.md>), [debugging](<https://devfeed.tech/topics/debugging.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [api](<https://devfeed.tech/tags/api.md>), [debugger](<https://devfeed.tech/tags/debugger.md>), [llms](<https://devfeed.tech/tags/llms.md>), [macos](<https://devfeed.tech/tags/macos.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [rust](<https://devfeed.tech/tags/rust.md>)

## AI overview

This article presents Snippy, an open-source screen-sharing GPT assistant that sends application screenshots with chat messages. It explains how GPT-4 with vision uses screen context to answer questions and describes the use of Tauri and Rust in the application.

## Source excerpt

While I no longer work on WinDbg, I still spend a lot of time thinking about how to make tools so people can build things faster. With WinDbg, I tried to do that by putting more debugging power at people's fingertips in a way that was easier to use. Recently, everyone is looking for ways to use LLMs to build things faster. But for most people using something like ChatGPT means pasting text back and forth between your different tools.