Open Interpreter

What is Open Interpreter?

Open Interpreter is an open-source coding agent that runs in your terminal and is tuned for low-cost models. It is a Rust fork of OpenAI's Codex, and its main idea is harness emulation: the /harness command switches between harnesses such as native, claude-code, kimi-code, qwen-code, deepseek-tui, swe-agent and minimal, so each model gets the tool setup it performs well with. You start a session by typing i or interpreter, switch providers and models with /model, and can run any OpenAI-compatible provider through Chat Completions. Commands run inside native sandboxing on macOS, Linux and Windows. It also runs as an Agent Client Protocol agent for compatible editors with interpreter acp, speaks the Codex exec protocol so Codex SDK projects can point at it, and reads shared AGENTS.md files and .agents/skills folders. A built-in QA skill can drive web apps through agent-browser and native apps through trycua. The code is released under Apache-2.0, and no paid plans are listed.

Use cases

• Run a coding agent in the terminal on low-cost models
• Switch model harnesses with one command
• Use an agent inside ACP-compatible editors
• Swap in for the Codex SDK with a one-line override
• Test web and native apps with the QA skill
• Reuse AGENTS.md and shared skills across agents

Who it's for

• Developers
• Terminal users
• AI agent builders
• Teams watching model costs

Why use Open Interpreter

• Lets inexpensive models behave closer to how their own vendors' agents do, by copying the harness each model family expects.
• Fits an existing setup, since it reads AGENTS.md, shared skills, MCP and ACP instead of its own private formats.
• Replaces the Codex binary in SDK code with one line, so existing automations keep their structure.
• Keeps configuration and session history on your machine in readable local files.
• Runs commands under native sandboxing and approval controls rather than unrestricted shell access.

Open Interpreter features

• Harness emulation via /harness, including claude-code, kimi-code, qwen-code and swe-agent
• Provider and model switching from the TUI with /model
• OpenAI-compatible providers through Chat Completions
• Native sandboxing on macOS, Linux and Windows
• Agent Client Protocol mode with interpreter acp
• Codex exec protocol compatibility for Codex SDK projects
• Support for exec, MCP, skills, hooks, permissions and AGENTS.md
• Built-in QA skill for testing web and native apps
• Shared .agents/skills directories
• Config and session state kept locally under ~/.openinterpreter

Open Interpreter integrations

• MCP
• Agent Client Protocol
• Codex SDK
• agent-browser
• trycua
• Kimi
• DeepSeek
• Z.AI

How to get started with Open Interpreter

1. Install with the curl script on macOS or Linux, or the PowerShell script on Windows.
2. Start a session by entering i or interpreter in your terminal.
3. Pick a provider and model with /model, following the provider setup guide for your key.
4. Use /harness to select the harness that matches the model, such as kimi-code or claude-code.
5. Optionally launch interpreter acp from an editor, or point the Codex SDK at the interpreter binary.

Open Interpreter limitations

• The Rust version is a new rewrite based on Codex; the original Python project is a separate community-maintained fork
• You supply your own provider access, since model usage is billed by the provider
• It is terminal-first; a desktop or browser client needs the separate Interpreter Workstation project

Open Interpreter pricing

Open Interpreter is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

Open Interpreter alternatives

The main Open Interpreter alternatives listed on Debuly are Claude Code, Aider, OpenCode, Cline, Gemini CLI and Kilo Code. The table compares pricing and platforms; order is A–Z.

1. Ai

   Aider

   Open-source AI pair programming tool that runs in your terminal and edits code in your local git repository using the LLM you choose.

   CodingDeveloper platforms
   Open sourceVisit Aider (official site)
2. 

   Claude Code

   Anthropic's coding agent that fixes bugs, writes tests and runs migrations from your terminal, IDE, desktop app, web or Slack.

   CodingAutomation and agentsDeveloper platforms
   PaidVisit Claude Code (official site)
3. 

   Cline

   Open-source AI coding agent for VS Code, JetBrains, the terminal and desktop that edits files and runs commands with your approval.

   CodingDeveloper platformsAutomation and agents
   Open sourceVisit Cline (official site)
4. 

   Gemini CLI

   Open-source command-line agent from Google that runs Gemini models in your terminal to read, edit and automate work in local projects.

   CodingAutomation and agentsDeveloper platforms
   Open sourceVisit Gemini CLI (official site)
5. 

   Kilo Code

   Open-source AI coding agent for VS Code, JetBrains and the CLI, with 500+ models, bring-your-own-key and team plans.

   CodingDeveloper platformsAutomation and agents
   FreemiumVisit Kilo Code (official site)
6. 

   OpenCode

   Open-source AI coding agent for terminal, desktop and IDE, with optional low-cost Go model subscriptions and a team Console

   CodingDeveloper platformsAutomation and agents
   FreemiumVisit OpenCode (official site)

Open Interpreter FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from avatars.githubusercontent.com · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.