local-ai

Deploy Codex with codex-keysmith

Name: Deploy Codex with codex-keysmith
Author: Jia-Ethan

Version-independent deployment, with codex-keysmith.

4,302 stars676 forksPythonGuide quality 8/10Updated 9/5/2026100% free · open source

What it does

Codex-keysmith enables version-independent deployment of Codex instructions with features like dry-run, backups, hook isolation, and recovery for reliable AI model management.

When to use it

•When deploying Codex models across different environments with varying version requirements
•When needing to test and validate Codex instructions before applying them to production models
•When requiring backup and recovery mechanisms for Codex models to prevent data loss

Ready-to-paste prompt

python -m codex_keysmith apply --instructions {'function': 'sum', 'args': [1, 2, 3]} --model my_codex_model

Heads up: Ensure that the Python version is compatible with the Codex-keysmith library, as it may require specific version dependencies or configurations

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/codex-keysmith && curl -fsSL https://workflowstacks.com/api/skills/codex-keysmith/claude-skill -o ~/.claude/skills/codex-keysmith/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Deploy Codex with codex-keysmith works

Codeflow

Free to inspect

Deploy Codex with codex-keysmith is a large Python project (~15k lines across 68 code files, plus 27 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, MIT license, has a test suite.

Size

Large codebase

~15k lines · 68 code files · ~2 h to skim

Setup

One-command install

Installs like a normal app. Reading the code is optional.

Runs on

Python

No API keys detected

Python 85%JavaScript 14%Rust 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
pyproject.toml
Dependencies and the commands it exposes
3
examples/gpt-contract.md
A worked example — copy this to get going

What's in each folder

docs/Documentation35 files

examples/Examples you can copy4 files

gui/Folder114 files

scenarios/Folder45 files

fixture_packs/Folder27 files

scripts/Helper scripts6 files

tests/Tests — proof it works25 files

.github/CI / automation (GitHub Actions)6 files

READMEHas testsDocumentedCI checksExamples includedMIT licenseUpdated this month