OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Local & Self-hosted AI

Hilbertraum

Hilbertraum is a desktop AI workspace that runs local models and can answer questions about private documents and optional offline Wikipedia sources, with prompts and workspace data stored on the user's computer.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Hilbertraum — OpenViST project profile in Local & Self-hosted AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want local-model chat or document and offline-reference question answering on a Windows, macOS or Linux computer, and are prepared to install the app, AI engine and model.

Who it is for

  • People who want to ask questions about private files using a local AI model.
  • Users who need offline access to Wikipedia or other ZIM-based knowledge packs.
  • Developers interested in a GPL-3.0 desktop AI application or its optional local completion API.

Documented uses

  • Chat with a local language model without a cloud fallback.
  • Import documents and ask questions with answers grounded in cited source passages.
  • Search offline Wikipedia and other registered ZIM knowledge packs alongside documents.
  • Summarize, translate or compare documents, and use listed local image, audio, dictation and OCR tasks.
  • Let another program on the same computer request model completions through the opt-in loopback API.
Before you choose

Requirements & limits

The repository documents prebuilt packages for Windows, Apple Silicon macOS and Linux. A working chat needs the separate AI engine and model. The stated minimum is 8 GB RAM. The project is licensed under GPL-3.0-or-later.

  • The app is local-first: the project states there is no cloud fallback, web search or telemetry.
  • Document Q&A uses vector and keyword retrieval with a reranker, citations and several ways to scope sources.
  • Offline knowledge packs require ZIM archives and kiwix-tools, an optional component.
  • Local image, audio, translation and OCR tasks need their associated local models or supporting files.
  • The local API is opt-in, limited to completions, and described as a loopback endpoint that does not expose documents or conversations.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the desktop app and local AI

Install the app and add the components required for a working local AI chat.

Before you start

  • A Windows, macOS or Linux computer with at least 8 GB RAM.
  • A prebuilt desktop package from the project releases, or a source build.

Steps

  1. Download and install the prebuilt app for your platform.

  2. Open the app and follow its prompts to add the AI engine and a model; both are required for working chat.

  3. If using Linux, make the AppImage executable before starting it.

Expected outcome

The app has a local AI engine and model available for chat.

Guide limitations

  • The app download does not include the AI engine or model; these are separate downloads.
  • The documented prebuilt macOS package is for Apple Silicon. Windows and macOS packages are unsigned, and the project notes that operating-system security prompts may appear.
  • An offline Wikipedia knowledge pack is a separate optional setup requiring kiwix-tools.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
HilbertraumAI/HilbertRaum · Official homepage title · retained in its source language
How we review sourcesSuggest a correction