AI templates

46 AI apps you can install on your own server. 35 run as one container and 11 as several services, 29 list an arm64 image, 3 are verified on a real host.

  • 46 templates
  • 64 MiB to 8 GiB memory, median 2 GiB
  • 29 list arm64
  • 3 verified
  • 7 licences
Submit a template

AI All templates

46 templates

  • AI Agentgateway Proxy built for agent traffic that routes MCP, A2A and LLM requests. The install form carries config.yaml as an editable file, so it starts with a listener that answers on port 3000. Permissive Self-host Agentgateway
  • AI AnythingLLM A private chat workspace over your documents, with built-in RAG and support for local or hosted models. Permissive Self-host AnythingLLM
  • AI Argilla A collaboration tool for labelling and curating datasets for language model work. Permissive Self-host Argilla
  • AI Bifrost Fast open source LLM gateway that routes requests to many providers behind one OpenAI compatible API, with a web UI for keys and routing rules. Permissive Self-host Bifrost
  • AI Big-AGI A multi-model chat workspace with personas, side by side answers and voice, using your own API keys. MIT licensed. Keys stay in your browser unless you set them on the server. Permissive Self-host Big-AGI
  • AI ComfyUI A node-graph editor for building and running Stable Diffusion and other image generation pipelines. Self-host ComfyUI
  • AI Crawl4AI An open source web crawler API that turns pages into clean Markdown and structured data for LLM pipelines, with a built-in playground and MCP endpoint. API calls need the generated token as a Bearer header. VerifiedPermissive Self-host Crawl4AI
  • AI Docling Serve An API server that converts PDFs, Office files and images into Markdown, JSON or text for RAG pipelines, using the Docling library on CPU. MIT licensed. The image is about 5 GB, the interactive UI is at /ui and the API docs at /docs. There is no login, so keep it private or behind an auth proxy. Permissive Self-host Docling Serve
  • AI Hollama A minimal web chat client for Ollama and OpenAI compatible servers. MIT licensed. Add the address of your model server in settings. Permissive Self-host Hollama
  • AI Jupyter GPU Notebook JupyterLab with a CUDA-ready data science stack for training and experimenting with models. Self-host Jupyter GPU Notebook
  • AI Kokoro TTS A CPU text-to-speech server with an OpenAI-compatible /v1/audio/speech API, built on the Kokoro model. Apache-2.0 licensed. The image is about 3 GB and there is no login, so keep it on a private network or behind an auth proxy. Permissive Self-host Kokoro TTS
  • AI Label Studio A flexible data labeling tool for text, images, audio, and video, with export to common ML formats. Permissive Self-host Label Studio
  • AI Langflow A visual low-code tool for building and deploying multi-agent and RAG workflows in Python. Permissive Self-host Langflow
  • AI Langfuse Trace, evaluate, and debug LLM applications with prompt management and cost analytics. Permissive Self-host Langfuse
  • AI LibreChat A self-hosted ChatGPT-style interface for many model providers, with agents, search, and multi-user login. Permissive Self-host LibreChat
  • AI LightRAG Graph based retrieval augmented generation server with a web UI and API. Runs on local file storage; point it at a model provider with the LLM and embedding settings. Permissive Self-host LightRAG
  • AI LiteLLM Proxy One OpenAI-format gateway in front of 100+ model providers, with keys, budgets, and spend tracking. Self-host LiteLLM Proxy
  • AI llama.cpp Server The llama.cpp HTTP server: run quantized GGUF models on plain CPUs with an OpenAI-compatible API. Permissive Self-host llama.cpp Server
  • AI Lobe Chat A modern, open-source AI chat framework supporting many model providers. Self-host Lobe Chat
  • AI LocalAI A drop-in OpenAI-compatible API that runs language, image, and speech models on your own hardware. Permissive Self-host LocalAI
  • AI MetaMCP An MCP aggregator and gateway that groups many MCP servers behind one endpoint with auth, namespaces and middleware. Permissive Self-host MetaMCP
  • AI MindsDB A query layer that connects data sources and AI models so you can ask questions in SQL. MIT licensed. Includes the web editor and the HTTP API. Permissive Self-host MindsDB
  • AI MLflow Track experiments, compare runs, and manage models with a self-hosted MLflow tracking server. Permissive Self-host MLflow
  • AI n8n AI Starter Kit n8n wired to a local Ollama model and a Qdrant vector store, ready for private AI workflows. Self-host n8n AI Starter Kit
  • AI n8n MCP A Model Context Protocol server that gives AI assistants searchable n8n node documentation. MIT licensed. The bearer token is generated for you. Permissive Self-host n8n MCP
  • AI New API An LLM gateway and AI asset management system that unifies many model providers. Network copyleft Self-host New API
  • AI Ollama A local LLM runtime with an HTTP API. Pull any model yourself once it's running. Permissive Self-host Ollama
  • AI Ollama + Open WebUI A local LLM runtime paired with a ChatGPT-style web interface, for running open models on your own hardware. Self-host Ollama + Open WebUI
  • AI Ollama: DeepSeek-R1 7B DeepSeek's R1 distilled 7B reasoning model, served locally through Ollama's HTTP API. Permissive Self-host Ollama: DeepSeek-R1 7B
  • AI Ollama: Llama 3 8B Meta's Llama 3 8B model, served locally through Ollama's HTTP API. Permissive Self-host Ollama: Llama 3 8B
  • AI Ollama: Mistral 7B Mistral's 7B instruct model, served locally through Ollama's HTTP API. Permissive Self-host Ollama: Mistral 7B
  • AI Ollama: Phi-3 Mini Microsoft's Phi-3 Mini (3.8B), the smallest model in this catalog, good for constrained nodes. Permissive Self-host Ollama: Phi-3 Mini
  • AI Ollama: Qwen 2.5 7B Alibaba's Qwen 2.5 7B model, served locally through Ollama's HTTP API. Permissive Self-host Ollama: Qwen 2.5 7B
  • AI Open Notebook An open source, self-hosted alternative to NotebookLM for researching with your own sources, with podcasts and chat. Add model provider keys in the app after install. VerifiedPermissive Self-host Open Notebook
  • AI Open WebUI A self-hosted chat interface for running local large language models through Ollama. Verified Self-host Open WebUI
  • AI OpenClaw A self-hosted personal AI agent gateway that connects chat apps and tools to the model provider you choose. Recommended container limit is 2 GiB. Measured use is 0.9 to 1.3 GiB, so a Levelrail VM needs at least 4096 MiB. The gateway trusts the ingress proxy through gateway.trustedProxies, written once to openclaw.json in the data volume. Permissive Self-host OpenClaw
  • AI Paperless-AI Adds automatic tagging, titles and document chat to a Paperless-ngx server using your choice of AI provider. MIT licensed. A setup wizard collects the Paperless address and token. Permissive Self-host Paperless-AI
  • AI Promptfoo Test and compare prompts, models and agents with a local web UI for browsing evaluation results. Runs the viewer with results stored on a volume. Permissive Self-host Promptfoo
  • AI SillyTavern A local chat front end for language models with characters, lorem books and extensions, bringing your own model API. AGPL-3.0 licensed. Sign in with the admin user and the generated password. Network copyleft Self-host SillyTavern
  • AI Speaches An OpenAI-compatible speech server: Whisper transcription and text-to-speech behind one API. Permissive Self-host Speaches
  • AI Stable Diffusion WebUI A browser interface for generating and editing images with Stable Diffusion checkpoints. Network copyleft Self-host Stable Diffusion WebUI
  • AI Text Embeddings Inference A lean server that turns text into embeddings with popular open models, on CPU with no extra setup. Permissive Self-host Text Embeddings Inference
  • AI Unstructured An API that turns PDFs, Word files, and other documents into clean data for RAG pipelines. Permissive Self-host Unstructured
  • AI vLLM A fast, high-throughput inference server that exposes an OpenAI-compatible API for open-weight language models. Permissive Self-host vLLM
  • AI Wyoming openWakeWord Local wake word detection over the Wyoming protocol for Home Assistant voice assistants, preloaded with the ok nabu model. Permissive Self-host Wyoming openWakeWord
  • AI Wyoming Piper Fast local text to speech over the Wyoming protocol, used by Home Assistant voice assistants. Downloads the chosen voice on first start. Permissive Self-host Wyoming Piper