ChatCodex is a local gateway that connects ChatGPT to the official Codex, enforcing user approval for every command, file write, or patch within a restricted workspace to ensure safe AI-driven code operations.

Stars

8

7-day growth

No data

Forks

1

Open issues

0

License

No data

Last updated

2026-07-28

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It adds a critical security layer by requiring explicit user consent for each potentially dangerous action, addressing a key concern of trusting AI with local system access.

Who it is for

  • Developers using ChatGPT for code assistance
  • Security-conscious users who want to control AI actions
  • Teams needing auditable approval workflows for AI-driven operations
  • Self-hosters who prefer local control over cloud-based solutions

Use cases

  • Applying code patches suggested by ChatGPT with manual approval
  • Running shell commands in a sandboxed workspace under user supervision
  • Allowing ChatGPT to read and write files within a project directory with oversight
  • Testing Codex capabilities in a controlled local environment before deployment

Strengths

  • Granular approval system for every write, command, and patch
  • Workspace sandboxing prevents access outside designated directories
  • Separate authentication tokens for console and ChatGPT reduce risk of compromise
  • Uses official unmodified Codex, ensuring compatibility and trust

Considerations

  • Requires local setup and public exposure (via tunnel or direct) for ChatGPT access
  • Default 5-minute approval timeout may interrupt long tasks
  • Currently integrates only with ChatGPT's Connector feature, limiting client options

README quick start

快速开始

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482