# AmberSahdev/Open-Interface

Control Any Computer Using LLMs.

Repository: https://github.com/AmberSahdev/Open-Interface
Canonical: https://ross.abutalabs.com/products/open-interface
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: gpt, llm, machine-learning, macos, openai, python, automation, assistant, assistant-computer-control, gpt4, gpt4v, gpt4vision, linux, pyautogui, pyinstaller, self-driving, self-driving-software, windows
Last push: 2026-07-17T02:26:26+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 92, release rhythm 28, longevity 68
- inputs: {"age_days": 952, "days_push": 48, "days_rel": 535, "gap_med": 34, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2715, forks 277 (observed 2026-08-28T04:07:12.018195+00:00)

## What it is
Open Interface is a cross-platform desktop application that lets users control their computer using natural language requests processed by LLM backends like GPT-4o and Gemini. It plans the required steps, simulates keyboard and mouse input via PyAutoGUI, and course-corrects using screenshots of progress.

## Use cases
- control my computer with natural language
- automate tasks on my desktop using an LLM
- have an AI agent operate my mouse and keyboard
- solve Wordle automatically with AI
- create documents hands-free with a computer autopilot
- self-driving software for my computer

## When to choose
- you want an open-source LLM agent that directly controls a desktop GUI
- you need cross-platform (macOS, Linux, Windows) computer automation
- you want screenshot-based feedback loops for task course-correction

## When to avoid
- you need headless server automation without a GUI
- you require guaranteed reliability or strict security, since simulated input can be error-prone
- you only want simple scripting without LLM costs or API dependencies

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, workflow-automation, computer-vision, gui
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: windows, python, cross-platform
- tags: computer-control, self-driving-computer, pyautogui, gpt-4o, screen-understanding, desktop-automation, llm-agent, ai-agents, automation, macos, linux, desktop

## Member repositories
- AmberSahdev/Open-Interface (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:12.018195+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:15:22.003542+00:00, confidence not recorded.
  - readme: https://github.com/AmberSahdev/Open-Interface (fetched 2026-08-28T04:07:12.018195+00:00, sha 981ca0e9a0b4)
- Data as of 2026-08-30T08:39:29.467469+00:00.