openinterpreter/openinterpreter — Gitpedia

<h1 align="center">Open Interpreter</h1> <p align="center">A coding agent for low-cost models.</p> <p align="center"> <a href="https://discord.gg/Hvz9Axh84z"><img alt="Discord" src="https://img.shields.io/discord/1146610656779440188?style=flat-square&label=Discord" /></a> <a href="https://www.openinterpreter.com/docs/terminal"><img alt="Documentation" src="https://img.shields.io/badge/Documentation-white?style=flat-square" /></a> <a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/License-Apache--2.0-white?style=flat-square" /></a> </p> <p align="center"> <a href="https://www.openinterpreter.com/docs/terminal"> <img alt="A close-up of a laptop screen running a terminal agent" src="https://www.openinterpreter.com/blog/open-interpreter-1-0/blog-hero-1.jpg" width="720" /> </a> </p>

[!NOTE]
This is the new Rust version of Open Interpreter. Looking for the original Python project? It lives on as a community-maintained fork at endolith/open-interpreter.

Installation

macOS and Linux:

bash
curl -fsSL https://openinterpreter.com/install | sh

Windows:

powershell
irm https://openinterpreter.com/install.ps1 | iex

Then type i or interpreter in your terminal to start a session.

Harness Emulation

Open Interpreter is a fork of OpenAI's Codex, with a focus on emulating the agent harness that gets the best performance out of low-cost models.

Use /harness to switch the active harness:

text
> /harness

native
claude-code
claude-code-bare
kimi-cli
qwen-code
deepseek-tui
swe-agent
minimal

Read more in the harness docs and model provider docs.

Computer Use

Open Interpreter ships with a QA skill that lets any model operate and test interfaces. It can drive web apps in a real browser with agent-browser, or operate and test native apps with trycua.

Features

Runs commands inside native sandboxing on macOS, Linux, and Windows.
Switches providers and models from the TUI with /model.
Inspects or switches Rust-native model harnesses with /harness.
Tests web and native apps through the built-in QA skill.
Shares one local runtime across terminal tabs instead of starting a full agent runtime for every session.
Keeps config and session state local under ~/.openinterpreter.
Supports exec, MCP, skills, hooks, permissions, and AGENTS.md.