Skillget

openinterpreter

agent
Security Audit
Pass
Health Pass
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 8 days ago
  • Community trust — 64158 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This tool provides a natural language interface for your computer, allowing large language models to run code locally. It lets you perform general computer tasks—like editing files, controlling a web browser, and analyzing datasets—directly through a terminal chat interface.

Security Assessment
The overall security risk is High. By design, the system executes code (Python, JavaScript, Shell) directly on your local machine based on AI-generated outputs. While the README explicitly states that users are asked to approve code before it runs, the inherent risk of local code execution remains substantial. The rule-based scan flagged an `exec()` shell command execution inside the Mac installer script. There are no hardcoded secrets detected, and it does not request dangerous base permissions. However, the core functionality relies heavily on executing shell commands and requires network requests to communicate with AI providers (such as OpenAI's API).

Quality Assessment
The project is highly trustworthy from a community and maintenance perspective. It boasts an impressive 63,410 GitHub stars and is actively maintained, with the most recent code push occurring just two days ago. Furthermore, it is fully compliant with open-source standards, using the AGPL-3.0 license, and includes clear documentation and setup instructions.

Verdict
Use with caution: The project is highly reputable and actively maintained, but its core design of executing AI-generated code locally requires strict human oversight on every prompt.
SUMMARY

A lightweight coding agent for open models like Deepseek, Kimi, and Qwen

README.md

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

Reviews (0)

No results found