hermes-cloudgpu

A Hermes Agent model-provider plugin for cloudgpu.app.

Hermes runs its own agent loop against cloudgpu.app's OpenAI-compatible API at https://cloudgpu.app/v1, with DeepSeek, Kimi, GLM and MiniMax models on one key. Model prices are on cloudgpu.app/api; the balance is topped up by card or USDT.

Setup

hermes plugins install cloudgpu-provider && export CLOUDGPU_API_KEY=cgw-sk-... && hermes chat --provider cloudgpu -m deepseek-v4.1-flash

Create the key in the cloudgpu.app console. Put it in ~/.hermes/.env to keep it; the installer also asks for it.

Before the catalog entry is merged, install from GitHub instead:

hermes plugins install mrhy7176/hermes-cloudgpu/model-providers/cloudgpu

Then hermes model and pick CloudGPU.

What it does


Provider id	`cloudgpu` (aliases `cloudgpu-app`, `cloudgpu.app`)
Base URL	`https://cloudgpu.app/v1` (override with `CLOUDGPU_BASE_URL`)
Auth	`CLOUDGPU_API_KEY`, sent as `Authorization: Bearer`
Model list	live from `GET https://cloudgpu.app/v1/models` (public); if that fails, the fallback list below
Default model	`deepseek-v4.1-flash` (also the auxiliary model)

Fallback models: deepseek-v4.1-flash, deepseek-v4-pro, kimi-k3, kimi-k2.7-code, glm-5.2, minimax-m3.

The plugin registers one provider profile and nothing else: no tools, hooks, middleware or extra dependencies. Prompts, tool schemas and the key go to cloudgpu.app.

Check it

hermes plugins validate --install-deps model-providers/cloudgpu

License

MIT.

cloudgpu-provider

What it adds

Environment variables it needs 1

README