dsh-oai-oauth
Run the following command in DeepSeek Harness:
dsh plugin install werifu/dsh-oai-oauth
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install werifu/dsh-oai-oauth in your terminal to install the plugin from https://github.com/werifu/dsh-oai-oauth into DeepSeek Harness.
About this plugin
If you already pay for ChatGPT Plus or Pro but cannot wire OpenAI models into DeepSeek Harness because you lack an API key, dsh-oai-oauth is the missing link. It plugs in as a DSH LLM adapter that reuses the OAuth credentials your local Codex CLI already stores, so you skip the whole cycle of requesting, rotating, and safeguarding an API key and stop worrying about per-token billing.
Setup is straightforward: head to Settings → Models in DSH, pick OpenAI ChatGPT (OAuth), and sign in once with your ChatGPT account. Every inference call after that travels over the OAuth channel on your existing subscription quota, and the auth state stays in sync with Codex CLI-re-authorize whenever the session expires.
It is built for developers who already hold a ChatGPT subscription, want OpenAI models inside a DSH workflow, and prefer to avoid carrying extra API credentials. Whether you are pairing with code, prototyping, or running prompt experiments, you get familiar models on familiar terms without the operational overhead of key management.
Screenshots
Use Cases
- Use OpenAI models in DSH without requesting or managing an API key
- Leverage your existing ChatGPT subscription for daily inference and prompt experiments
- Integrate OpenAI models into a DSH workflow alongside other providers under unified scheduling
Best For
- Developers with a ChatGPT Plus or Pro subscription who want zero-cost OpenAI model access
- Engineers who prefer a single credential management flow over juggling multiple API keys
- Teams that rely on OpenAI models for code completion, prototyping, or batch inference within DSH
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.