Open Interpreter

A terminal coding agent tuned for low-cost open models such as Kimi and GLM, now built as a fork of OpenAI's Codex with switchable agent harnesses.

68.8k stars, 5.9k forks Rust On GitHub since July 2023

Visit website View on GitHub How to run it

What is Open Interpreter?

Open Interpreter began in 2023 as a tool that let language models run code on your computer. Today it is a coding agent forked from OpenAI's Codex and rewritten around one idea: each model performs best with the agent harness its provider recommends. A /harness command switches between emulated harnesses, for example the Kimi Code harness reimplemented in Rust for Kimi K3. It keeps a Codex-like interface, works with the Agent Client Protocol, and starts with i or interpreter in the terminal.

Good fit if

  • You use inexpensive open models and want the best results from each.
  • You like Codex's interface but want to use non-OpenAI models.

Look elsewhere if

  • You mainly use one frontier model through its vendor's agent: Codex CLI or Qwen Code.
  • You want an agent inside your IDE: Cline.

Before you adopt it

Open Interpreter is Apache-2.0, and contributors sign a contributor license agreement with the project. The tool has changed character completely since its first versions, so older tutorials no longer apply.

Drafted with AI from the project's README and repository data, then checked against that data on 30 October 2026. Report a correction

Open Interpreter health: is it still maintained?

81 of 100, actively developed

  • Activity
    1,685 commits in the last 90 days, the latest on 1 November 2026.
    30 / 30
  • Contributors
    13 people wrote the latest 100 commits; the most active wrote 39% of them.
    15 / 20
  • Releases
    15 releases in the last 12 months; the latest, rust-v0.0.57, on 31 October 2026.
    19 / 20
  • Replies to issues
    Maintainers answered 27% of recent issues, with a median first reply after 38 hours.
    12 / 20
  • Security practices
    No OpenSSF Scorecard for this repository yet, so this part gets a neutral score.
    5 / 10

Read from GitHub on 1 November 2026. How the score works

Open Interpreter license: is it open source?

Open Interpreter uses Apache-2.0, an open-source license approved by the OSI. Contributors sign a contributor license agreement, which lets the owner relicense their work later.

  1. July 2023First published on GitHub.
  2. TodayApache-2.0. A contributor license agreement is required.

How to run Open Interpreter yourself

Docker
Dockerfile or compose file in the repository
Compose file
None in the repository
Setup effort
Not rated: no compose file to judge from
Kubernetes
No Helm chart in the repository
Desktop and mobile
Builds for Linux, Windows in GitHub releases
Interface languages
English only

Install instructions: openinterpreter.com or the README on GitHub.

Alternatives to Open Interpreter

  • Qwen CodeAn open-source AI coding agent that lives in your terminal. 80 health · Apache-2.0 · 28.9k stars
  • CodewhaleOpen-source agent for the terminal written in Rust. Use any provider or model. Issues & PRs always welcome 82 health · MIT · 41.2k stars
  • Goosean open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test… 85 health · Apache-2.0 · 56.1k stars
  • RepomixRepomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for… 72 health · MIT · 29.1k stars
  • Browser UseOpen-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted… 64 health · MIT · 120k stars

All 27 projects in AI coding agents

Questions about Open Interpreter

Is Open Interpreter open source?

Yes. Open Interpreter is published under Apache-2.0, an OSI-approved open-source license.

Is Open Interpreter still maintained?

Its health score is 81 of 100 (actively developed). It had 1,685 commits in the last 90 days, the latest on 1 November 2026, and its latest release came out on 31 October 2026.

How do I run Open Interpreter?

You can run it with Docker, as an app for Linux, Windows. The README on GitHub has the exact steps.

What are the alternatives to Open Interpreter?

Close alternatives in the AI coding agents category include Qwen Code, Codewhale, Goose.