openinterpreter
A lightweight coding agent for open models like Deepseek, Kimi, and Qwen
Running a lightweight, open-source coding agent locally with open models.
You want a managed product with support and guardrails.
Documentation context
Check the current installer and model path
The current Open Interpreter repository describes a coding agent for open models. Its present setup differs from older descriptions of a general computer interpreter; follow the documentation for the version you intend to use.
A locally installed interface does not establish that inference, files or logs stay on your device. Check model endpoints, tools and providers. This documentation note does not refresh every stored catalogue field or report a hands-on test.
About openinterpreter
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.
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.
openinterpreter is listed in this index written primarily in Rust, with 69k stars on GitHub. Its latest recorded repository push was in November 2026; that is not an ASE editorial review date.