GStars
    openinterpreter

    openinterpreter/openinterpreter

    #74 this week

    A coding agent for open models like Kimi K3

    backend
    acp
    coding-agent
    deepseek
    kimi
    qwen
    Rust
    Apache-2.0
    66.6K stars
    5.7K forks
    66.6K GitHub watchers
    Updated 7/18/2026
    View on GitHub

    Backblaze Generative Media Hackathon

    Build the next generation of AI media apps with Genblaze, stored on Backblaze B2. $10,000 in prizes.

    Enter the hackathon

    Loading star history...

    Use Cases & Benefits

    • Provides a lightweight coding agent that runs and tests code using low-cost AI models with native sandboxing across major operating systems.
    • Enables flexible switching between multiple AI model harnesses and providers directly from a terminal user interface for optimized performance.
    • Use for automating code execution and testing in native and web applications through integrated QA skills and sandboxed environments.
    • Use for integrating AI-driven coding assistance into editors via the Agent Client Protocol to enhance developer workflows.
    • Use for experimenting with and benchmarking various open AI models like Deepseek, Kimi, and Qwen in a unified Rust-based tool.

    About openinterpreter

    Open Interpreter

    A coding agent for low-cost models.

    Discord Documentation License

    A close-up of a laptop screen running a terminal agent

    [!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:

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

    Windows:

    irm https://www.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:

    > /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.
    • Runs as an Agent Client Protocol agent for editors with interpreter acp.
    • Keeps config and session state local under ~/.openinterpreter.
    • Supports exec, MCP, skills, hooks, permissions, and AGENTS.md.

    Documentation

    License

    Apache-2.0

    Discover Repositories

    Search across tracked repositories by name or description