← Discover
GitHub · openinterpreter/openinterpreter↑ +299 today

Artificial intelligence that runs code on your computer

Open Interpreter offers a coding agent that automates software development processes by running code in the local computer environment. Designed to work with low-cost language models, this tool allows executing complex tasks directly from the terminal.

Updates

  • November 4, 2026: Stars 68,776 → 68,790, latest release rust-v0.0.59 (November 4, 2026).
  • November 2, 2026: Stars 68,768 → 68,776, latest release rust-v0.0.58 (November 1, 2026).
  • November 1, 2026: Stars 68,521 → 68,768, latest release rust-v0.0.57 (October 31, 2026).
  • October 7, 2026: Stars 68,478 → 68,521, latest release rust-v0.0.56 (October 7, 2026).

What you get

  • It automates software processes via the local terminal.
  • It is compatible with low-cost language models.
  • Offers the ability to test web and native applications.

Installation

Installation for macOS and Linux
curl -fsSL https://www.openinterpreter.com/install | sh

Running it

Start session
i

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want you to act as a coding agent on my computer. I expect you to automate complex tasks by running code in my local environment, testing web or local applications when necessary. Use structures that optimize low-cost models when performing transactions and execute my commands safely through the terminal.

Repository: https://github.com/openinterpreter/openinterpreter. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

Who it is forIt is suitable for users who want to automate their software development processes via the terminal.
LicenseApache-2.0

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-07-16: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.