Skip to main content

AI Service Templates

The AI Services category contains 23 templates covering LLM inference servers, chat interfaces, AI automation platforms, and specialized AI tools.

These flagship templates are highlighted in the catalog:

TemplateDescriptionMin RAM
OpenClawOpen-source AI assistant platform with multi-model support2 GB
LibreChatMulti-provider AI chat interface (OpenAI, Anthropic, local models)1 GB
OllamaLocal LLM inference server — run models on your hardware4 GB
DifyLLM application development platform with visual workflow builder2 GB

Complete Template List

TemplateDescriptionCategoryMin RAMSecurity
OpenClawOpen-source AI assistant platformChat2 GBsecure
LibreChatMulti-provider AI chat interfaceChat1 GBsecure
OllamaLocal LLM inference serverInference4 GBadvanced
DifyLLM app development platformPlatform2 GBsecure
Open WebUIWeb interface for Ollama and OpenAI-compatible APIsChat512 MBsecure
LiteLLMOpenAI-compatible proxy for 100+ LLM providersProxy512 MBsecure
LocalAISelf-hosted OpenAI-compatible APIInference4 GBadvanced
Text Generation WebUIGradio web UI for large language modelsChat4 GBadvanced
FlowiseDrag-and-drop LLM flow builderPlatform1 GBsecure
LangflowVisual framework for building LLM applicationsPlatform1 GBsecure
AnythingLLMAll-in-one AI desktop app turned self-hostedChat1 GBsecure
JanOpen-source ChatGPT alternative, runs offlineChat2 GBsecure
GPT4AllLocal LLM chat with privacy focusChat4 GBadvanced
SergeSelf-hosted chat interface using llama.cppChat2 GBsecure
SillyTavernAI chat and roleplay frontendChat512 MBsecure
Stable Diffusion WebUIImage generation with Stable Diffusion modelsImage8 GBadvanced
ComfyUINode-based Stable Diffusion workflow editorImage8 GBadvanced
WhisperOpenAI Whisper speech-to-text serverAudio2 GBsecure
Coqui TTSDeep learning text-to-speech serverAudio2 GBsecure
HaystackLLM orchestration framework for RAG pipelinesFramework1 GBsecure
ChromaAI-native open-source vector databaseDatabase1 GBsecure
QdrantHigh-performance vector similarity search engineDatabase1 GBsecure
WeaviateVector database for AI applicationsDatabase2 GBsecure

GPU Support

Templates marked with advanced security profile may support GPU passthrough. For GPU-accelerated inference (Ollama, LocalAI, Stable Diffusion), ensure your server has:

  • NVIDIA GPU with CUDA support
  • nvidia-container-toolkit installed
  • Docker configured with the NVIDIA runtime

The template variables include GPU configuration options when applicable.

Connecting AI Services

Many AI services work well together. Common combinations:

  • Ollama + Open WebUI — Local inference with a polished chat interface
  • Ollama + LiteLLM — Local inference exposed as an OpenAI-compatible API
  • Dify + Ollama — Visual AI workflow builder using local models
  • LibreChat + LiteLLM — Multi-provider chat routing through a single proxy

Services deployed on the same panel can communicate over the internal Docker network using their service names as hostnames.