dsh-openai-codex
Run the following command in DeepSeek Harness:
dsh plugin install bufeibufei/dsh-openai-codex
Paste the following prompt into your AI chat to install this plugin:
Install the plugin in DeepSeek Harness using the command dsh plugin install bufeibufei/dsh-openai-codex, with the source code at https://github.com/bufeibufei/dsh-openai-codex.
About this plugin
DeepSeek Harness, as an AI model inference framework, natively lacks support for OpenAI's Codex models, limiting users from exploring tasks like code generation within the environment. The dsh-openai-codex plugin experimentally bridges this gap by registering Codex models into the DSH adapter seam and managing OAuth authentication via ChatGPT subscriptions, allowing secure access without API keys. It is ideal for developers or researchers using DeepSeek Harness who wish to extend model capabilities, especially those with ChatGPT accounts, but they should be mindful of compatibility constraints, such as avoiding conflicts with built-in settings, to ensure stable integration.
Use Cases
- Integrate Codex models into DeepSeek Harness for code generation.
- Access Codex models via ChatGPT subscription without API keys.
- Experimentally test OpenAI Codex within a model inference framework.
Best For
- Developers using DeepSeek Harness.
- Researchers with a ChatGPT subscription.
- Engineers interested in model inference and code generation.
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.