Is openai/codex safe to download?

Name: Safety check of openai/codex
Item: openai/codex
Rating: 97
Author: SafeToClone

openai/codex gets an A (97/100) from SafeToClone: Trusted. 1 warning sign: Runs a script straight from the internet.

A97/100

openai/codex (opens in a new tab)

Trusted

Looks trustworthy. Still only install what you need.

Lightweight coding agent that runs in your terminal

View on GitHub Run the check again now

What should I do?

It's well known, looked after, and shows none of the malware tricks we check for. Download it only from its official GitHub page, never from a copy, a file-sharing site or a link in a video.

Warning signs 1

Runs a script straight from the internet Good to know

Checked Oct 21, 2026. We re-check this repo every night. A grade is a set of warning signs, not a guarantee. How we score

Other AI tools we graded

A97/100

langchain-ai/langchain

Trusted No warning signs

The agent engineering platform.

GitHub page for langchain-ai/langchain (opens in a new tab)
A97/100

ggml-org/llama.cpp

Trusted 1 warning sign

LLM inference in C/C++

GitHub page for ggml-org/llama.cpp (opens in a new tab)
A97/100

infiniflow/ragflow

Trusted No warning signs

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

GitHub page for infiniflow/ragflow (opens in a new tab)
A94/100

crewAIInc/crewAI

Trusted 1 warning sign

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

GitHub page for crewAIInc/crewAI (opens in a new tab)
A93/100

n8n-io/n8n

Trusted 2 warning signs

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

GitHub page for n8n-io/n8n (opens in a new tab)
A93/100

browser-use/browser-use

Trusted No warning signs

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

GitHub page for browser-use/browser-use (opens in a new tab)
A92/100

anthropics/claude-code

Trusted 1 warning sign

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

GitHub page for anthropics/claude-code (opens in a new tab)
A90/100

AUTOMATIC1111/stable-diffusion-webui

Trusted No warning signs

Stable Diffusion web UI

GitHub page for AUTOMATIC1111/stable-diffusion-webui (opens in a new tab)

See all 20 grades