Quickstart

Open Interpreter is a terminal coding agent built from the Codex CLI surface and adapted for provider-agnostic local use. It can inspect your repository, edit files, run commands, review diffs, and resume work later.

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

On Windows, run:

irm https://openinterpreter.com/install.ps1 | iex
Open a project
cd my-project
interpreter
Choose a provider

The first run walks you through provider setup. You can sign in with ChatGPT, use an API key, connect a local model through Ollama or LM Studio, or configure another compatible provider.

You can change providers later with /model.

Ask for a change

Type a concrete request:

add a /health endpoint that returns the build sha

Open Interpreter reads the project, proposes work, edits files, and runs commands through the active sandbox and approval settings.

Approve actions

In the default local workflow, Open Interpreter can work inside the current workspace and asks before actions that need more access. Use /permissions to inspect or change this during a session.

Resume later
interpreter resume --last

Resume keeps the prior conversation, context, and working directory.

Common first commands

TaskCommand
Start the TUIinterpreter
Start with a promptinterpreter "explain this repo"
Run once without the TUIinterpreter exec "summarize the current diff"
Continue the last sessioninterpreter resume --last
Review current changes/review or interpreter exec review --uncommitted
Choose model/provider/model
Change permissions/permissions

Next pages