@axiaisacat: ByteDance has open-sourced an AI called UI-TARS that can directly control your computer. It is open-source, free, and runs locally. You tell it using natural language: 'Book me the earliest flight from San Francisco to New York on September 1st on Priceline', 'Set the auto-save delay in VS Code to 500ms', '...'

X AI KOLs Timeline Models

Summary

ByteDance has open-sourced UI-TARS, an AI model capable of directly controlling computer interfaces via mouse and keyboard for tasks like booking flights or configuring software. Available in 2B, 7B, and 72B parameter sizes, it runs locally and offers a free alternative to paid services like Anthropic's Computer Use.

ByteDance has open-sourced an AI capable of directly controlling your computer, called UI-TARS. It is open-source, free, and runs locally. You instruct it using natural language: 'Book the earliest flight from San Francisco to New York on September 1st on Priceline' 'Set the auto-save delay in VS Code to 500 milliseconds' 'Check the weather in Hangzhou for this month and generate a chart' It doesn't just write code for you; it looks at your screen and operates the mouse and keyboard itself. It can control both browsers and desktop applications, with full MCP tool integration. Choose from model sizes of 2B, 7B, or 72B, running locally. Anthropic's Computer Use requires payment, and OpenAI's Operator requires a subscription. ByteDance has open-sourced the entire tech stack. This is arguably one of the most sincere open-source projects from a major Chinese tech company—there really isn't another like it.
Original Article

Similar Articles

bytedance/UI-TARS-desktop

GitHub Trending (daily)

ByteDance released TARS, a multimodal AI agent stack comprising Agent TARS (a CLI/Web UI-based general AI agent for GUI, browser, and terminal tasks) and UI-TARS Desktop (a native desktop application powered by the UI-TARS model for local and remote computer/browser automation). The stack integrates multimodal LLMs with MCP tools for human-like task completion.

@berryxia: Bros! Don't reinvent the wheel—just use this 31.4K-star open-source project! ByteDance has open-sourced UI-TARS-desktop. Taking a quick look, the project has been live for nearly a year! It currently has 31.4k stars, and its growth rate is quite steady. 24-hour growth...

X AI KOLs Timeline

ByteDance open-sourced UI-TARS-desktop, a native desktop GUI agent with 31.4k GitHub stars that uses vision models to control local or remote applications via natural language. The tool runs locally for privacy, supports Windows and macOS, and includes a CLI with streaming output for developers.