AI applications deployment templates
Build interfaces and services around AI models. Check whether a template needs external model credentials or local compute; deploying an interface does not include model inference credits.
26 templates · Page 1 / 2
AnythingLLM
Argilla
Chroma
Docling
Engram
Flowise
Deploy Flowise on Polyer to build LLM orchestration flows, chatbots and AI agents in a visual low-code editor. The template runs one public Flowise service; its SQLite database, encryption key, uploads and logs are stored on a volume at /root/.flowise. Review the generated credentials and the floating latest tag.
Flowise with Databases
Hermes Agent
Hermes Agent with WebUI
Honcho
Label Studio
Langflow
Langfuse
LibreChat
LibreTranslate
LiteLLM
Deploy LiteLLM on Polyer to run an OpenAI-compatible proxy in front of many LLM providers, with virtual keys and spend tracking. The template runs a public LiteLLM service with a private PostgreSQL 16 database and a private Redis cache, both on volumes. Review the provider API keys and the preconfigured model list.
LobeChat
MetaMCP
MindsDB
Ollama with Open WebUI
Run Ollama with Open WebUI on Polyer to deploy open-weight language models behind a self-hosted chat interface. The template creates a private ollama-api service with model storage on a volume, plus a public Open WebUI service. Polyer has no GPU: models run on CPU, so review memory, CPU and storage before pulling one.
Open WebUI
Deploy Open WebUI on Polyer for a self-hosted chat interface to AI models through OpenAI-compatible APIs or Ollama. The template runs one public Open WebUI service with no bundled model server; its data lives on a volume at /app/backend/data. Review the floating main image tag and the model connections you will add.
OpenClaw
Spacebot
How to choose
- For a chat interface, Open WebUI and LobeChat run as one service and LibreChat as 5, each using model APIs you supply. Ollama with Open WebUI runs models on CPU because Polyer has no GPUs, so plan for small models.
- To build LLM flows and agents visually, start with Flowise, which runs as one service or with databases as 4. It needs model API keys, and RAG flows can store embeddings in Chroma or Weaviate.
- To route model calls, LiteLLM (3 services) puts many providers behind one OpenAI-compatible API with a key per application. Its PostgreSQL database holds those keys and spend data, so back it up.