openinterpreter
/
openinterpreter
A lightweight coding agent for open models like Deepseek, Kimi, and Qwen
Open Interpreter
A coding agent for low-cost models.
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…
1. Create a virtual env
mkdir openInterpreter
cd openInterpreter
python -m venv venv openinterpreter_env
2. Activate venv
./openinterpreter_env/Script/activate
3. Install open-interpreter
pip install open-interpreter
4. Run Open Interpreter
The following command is to use gpt3.5 turbo.
interpreter --fast
Welcome to Open Interpreter.
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
▌ OpenAI API key not found
To use GPT-4 (recommended) please provide an OpenAI API key.
To use Code-Llama (free but less capable) press enter.
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Top comments (1)
On Windows 10, I got step 2 to work as:
openInterpreter> \openinterpreter_env\Scripts\activate