Base
Hardened build
minimal ports, security patches applied at build time
Ollama + AnythingLLM
Azure
Artificial Intelligence (AI)
1 variation
A private AI workspace in one VM: chat with your documents using open models that run locally, with no API key and nothing sent to a third party.
Variations
This product is available in the build below. Open it for the operating system, cloud and version detail, or read its deployment guide.
| Product | Cloud | Operating system | Version | |
|---|---|---|---|---|
| Ollama + AnythingLLM | Azure | — | Standard | View · Guide |
Overview
This bundle pairs two open source, MIT licensed projects into one ready to use private AI workspace. AnythingLLM is the web application: chat, retrieval augmented generation over your own documents, workspaces, AI agents and multi user accounts. Ollama is the local model server that runs open weight language models on the VM itself, here serving both the chat model AnythingLLM answers with and the embedding model it uses to index your documents.
Because the models run on the same machine, prompts, documents, embeddings and chats stay inside your own cloud account. It suits teams that want a self hosted alternative to hosted AI chat services for confidential material, and developers who want a local, OpenAI free stack to build on.
Why the cloudimg image
The cloudimg image arrives wired end to end: AnythingLLM is already connected to Ollama for both chat and embeddings, and two openly licensed models (IBM Granite 4.0 Micro for chat and Nomic Embed Text for embeddings, both Apache 2.0) are baked in, so the first chat works without downloading anything or entering a key. AnythingLLM's multi user mode is switched on with an admin password generated uniquely for each VM at first boot, the app is served over HTTPS by nginx, Ollama listens on loopback only and telemetry is turned off. The paired deployment guide covers sign in, document chat, the developer API, adding larger models and your own domain, and every deployment carries 24/7 support.
Common uses
- Private chat over confidential documents without sending them to an AI provider
- A self hosted, multi user AI assistant for a team
- A local LLM and RAG stack with an API for building internal tools
More in Artificial Intelligence (AI)
Argilla
Artificial Intelligence (AI)
Argilla, an open source data annotation and curation platform for building high quality datasets for natural language pr
Bifrost
Artificial Intelligence (AI)
one OpenAI compatible endpoint in front of every model provider, packaged by cloudimg
ContextForge MCP Gateway
Artificial Intelligence (AI)
ContextForge, the open source model context protocol gateway from IBM: federate many MCP servers behind one authenticate
Crawl4AI
Artificial Intelligence (AI)
an open source web crawler that turns any web page into clean, LLM ready markdown over a REST API, secured from first bo
Do
DeepWiki-Open
Artificial Intelligence (AI)
turn any Git repository into a browsable, AI generated wiki
Dify
Artificial Intelligence (AI)
Dify, a source available platform for building LLM apps, agents, RAG and workflows from a visual console.