AIquila

Private AI for your Nextcloud — your data, your server, your choice of AI provider

What is AIquila?

AIquila brings AI to your self-hosted Nextcloud. Instead of keeping your files, notes, tasks and recipes locked inside Nextcloud — or copying them by hand into a chat window — AIquila lets an AI assistant read and write your Nextcloud data directly. Your data stays on your own server, and you decide which AI provider sees it: a hosted API, or a model running on your own hardware that sends nothing to anyone.

How it works

AIquila has three components that can be used independently or together:

MCP Server — A Model Context Protocol server that gives any MCP-compatible AI assistant secure access to your Nextcloud. 349 tools across 44 categories: browse and manage files, keep calendars, tasks and contacts in sync, work in Talk, Deck and Mail, organise photos, notes and bookmarks, and run Coworkers and occ administration. It has no model of its own — it exposes Nextcloud to whichever MCP client you connect.

Nextcloud App — A native Nextcloud application that brings AI directly into the Nextcloud UI. Chat about your documents, summarise and rewrite text, run Coworkers (saved, repeatable AI jobs), and scope a conversation to a Project so the assistant only sees the folders you choose. Admins pick which providers are available, and may restrict them per user or group.

Hetzner Deployment — A single-command provisioning tool (aiquila-hetzner) that stands up a production-ready AIquila server on Hetzner Cloud, complete with Traefik reverse proxy, CrowdSec intrusion prevention, TLS, and optional monitoring.

AI providers

The Nextcloud app supports these providers for chat. Each user can pick a provider and model per conversation, within what the admin allows.

Provider	Hosting	Notes
Claude (Anthropic)	Anthropic API	The default, and the most deeply integrated: vision, thinking budgets, native MCP connector, and PDF handling with citations.
Claude on a cloud platform	Your AWS, Google Cloud or Azure account	The same Claude integration through Claude Platform on AWS, Claude on Google Cloud, Amazon Bedrock, Vertex AI or Microsoft Foundry, with the platform's billing, IAM and regions. Some platforms lack batches or the native MCP connector.
Hetzner Inference	Hetzner (German provider)	OpenAI-compatible. Currently an experimental Hetzner service, free while experimental. Hetzner is replacing it with an official product, and experiment tokens stop working on 8 December 2026. Hetzner states it does not store request and response content. No new tokens are issued.
Mistral	Mistral API (French provider)	Also supports the native MCP connector. Mistral offers EU-only processing through its regional inference endpoints.
Local model	Your own hardware	Ollama, LM Studio or llama.cpp. Nothing leaves your infrastructure. Supports bearer/basic/header auth and mTLS.
DeepSeek	DeepSeek API	OpenAI-compatible. No native MCP connector.

Provider choice applies to chat, the per-conversation model picker and the Nextcloud Assistant / TaskProcessing integrations, which all run on the provider the user has selected. Assistant actions that send images ("Analyze images", "Extract text from image") need a vision-capable provider, and report which of the available ones qualify when the selected provider is not.

Getting Started

Pick the path that fits your setup:

Path	What you get	Guide
npx aiquila-mcp	Local MCP client + Nextcloud	Quick start
Docker + OAuth	Remote MCP client + Nextcloud	Quick start
Nextcloud App	AI inside the Nextcloud UI	Quick start
Hetzner Cloud	Full production deploy	Quick start
Mobile + Voice	Phone + Nextcloud hands-free	Quick start

• Getting Started Guide — all five paths with step-by-step instructions
• Full Documentation — architecture, configuration, and advanced topics
• Nextcloud compatibility — which Nextcloud versions are supported, and what "supported" means

Contributing

Contributions are welcome. Please read CONTRIBUTING.md first — most importantly, open or comment on an issue before writing code, so we can confirm the approach before you invest the effort.

The guide covers branch and commit conventions, the checks CI runs per component, and what to expect from CI on a pull request from a fork.

Support

AIquila is free software and developed in the open. If it is useful to you, funding covers the running costs behind it — test servers, CI minutes, domains and the App Store presence:

• GitHub Sponsors
• Liberapay

Contributing time — issues, pull requests, documentation, or simply telling other people about the project — helps just as much.

License

AGPL-3.0 (Nextcloud App) / MIT (MCP Server)

See ACKNOWLEDGMENTS.md for the open-source projects and services AIquila is built on.