AI Applications
Application Types
- Application Orchestration: LLM applications, Agents, and workflows (Dify, OpenClaw, HermesAgent).
- Image Generation: Image and node-based workflows (ComfyUI).
For quick start steps of each application, jump directly to the corresponding page:
- OpenClaw Quick Start
- HermesAgent Quick Start
- Dify Quick Start
- ComfyUI Quick Start
- Application Templates
- AI Inference (Ollama)
OpenClaw
OpenClaw 🦞 is an open-source, self-hosted personal intelligent agent assistant that does not require a GPU. Once deployed, you can quickly create and use it from the console.
HermesAgent
Hermes Agent is an open-source autonomous AI agent from Nous Research. It supports persistent memory, tool use, and gateways to WeChat, QQ, Telegram, Discord, and more. On Cloudpods, Hermes is deployed as application type hermes-agent: the platform runs a container with a Web desktop and the Hermes Agent service.
Dify
Dify is an LLM application development and orchestration platform that supports building conversational, Agent, and workflow applications. Dify itself does not require a GPU and can run on nodes without an NVIDIA environment configured. Only when downstream inference services require a GPU do the corresponding inference instances need to meet GPU requirements.
ComfyUI
ComfyUI is an image generation and visual workflow application that supports node-based workflow orchestration, suitable for image generation, workflow reuse, and visual debugging.
Application Templates
Application templates are used to define the CPU/memory/GPU/storage configuration for AI application instances (such as OpenClaw, Dify, ComfyUI). When creating an instance, templates allow quick reuse of resource specs.