OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Mindgeniusai

Mindgeniusai is a self-hostable AI workspace that chats over PDFs using built-in retrieval-augmented generation and creates editable mind maps. Its multi-step agent exposes tool calls for document search, map generation, branch expansion and node-level edits.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Mindgeniusai — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a PDF-based research or knowledge task benefits from both document-grounded questions and a mind map that can be refined by people and the agent.

Who it is for

  • Researchers and knowledge workers who want to question PDFs and organize findings visually.
  • Self-hosters and teams handling sensitive research, legal documents or internal specifications.

Documented uses

  • Ask questions across one or more attached PDFs using retrieval.
  • Convert document material into a mind map and expand branches.
  • Manually edit map nodes or ask the agent to change specific nodes while preserving other edits.
  • Import Markdown or OPML maps and export maps in PNG, SVG, Markdown, OPML or Mermaid formats.
Before you choose

Requirements & limits

The repository offers a live demo that requires visitors to bring their own API key. Local development requires Node.js 20 or later and pnpm; the README also documents a Docker image. The repository identifies the license as BSL 1.1.

  • The README documents OpenAI and Claude with full RAG; DeepSeek and Kimi lack embeddings in this setup, with an OpenAI-compatible embedding endpoint offered as a way to keep retrieval enabled.
  • The app uses user-supplied model keys and supports OpenAI, Claude, DeepSeek, Kimi and OpenAI-compatible endpoints.
  • The canvas supports manual edits that the agent can take into account on a later message.
  • The project describes a self-hosted deployment and in-memory PDF processing; choose the infrastructure you control if that operating model matters.

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

Start Mindgeniusai locally with pnpm

Install and start the documented local development setup.

Before you start

  • Node.js 20 or later
  • pnpm
  • A model provider and API key, configured during setup or later in the app

Steps

  1. Run pnpm install.

  2. Run pnpm setup and select a provider and key; the wizard writes apps/server/.env.

  3. Run pnpm dev to start the web app on port 5173 and API on port 3000.

Expected outcome

The local web app and API are started for development.

Guide limitations

  • The README documents the development startup path, not a production deployment procedure.
  • DeepSeek and Kimi lack embeddings in the documented setup; configure an OpenAI-compatible embedding endpoint to keep RAG enabled.
Documentation 1 ↗
Source-based practical guide

Run the app with Docker

Start the documented single-image application locally.

Before you start

  • Docker
  • A model API key, or a plan for visitors to provide their own key in Settings

Steps

  1. Run the documented Docker image with port 3000 mapped to port 3000; provide OPENAI_API_KEY as an environment variable if using a server key.

  2. Open http://localhost:3000.

Expected outcome

The web application and API are served from the Docker image.

Guide limitations

  • The documented example uses an OpenAI key; the README also describes omitting the key so each visitor can provide one in Settings.
  • This recipe follows the README's documented command and is not a deployment or compatibility test.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
MindgeniusaiAsk questions across one or more attached PDFs using retrieval.Docker, Self-hosted, WebThe repository offers a live demo that requires visitors to bring their own API key. Local development requires Node.js 20 or later and pnpm; the README also documents a Docker image. The repository identifies the license as BSL 1.1.
VectaurantFind menu options by describing preferences, such as asking what is vegan or spicy.CLI, Docker, Linux, macOS
Aml Multiagent RagIngest PDF regulations, extract and chunk their text, and build a searchable vector collection.Docker, Self-hostedThe repository is public and specifies the MIT license. The documented setup is self-hosted and requires Python 3.11 or later, Docker Desktop and an OpenAI API key.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
xianjianlf2/MindGeniusAI · Official homepage title · retained in its source language
How we review sourcesSuggest a correction