MindGeniusAI
An AI agent that reads your PDFs and draws editable mind maps — visible tool-calling loop, built-in RAG, bring-your-own-key, multi-provider (OpenAI / Claude / D
What is MindGeniusAI?
An AI agent that reads your PDFs and draws editable mind maps — visible tool-calling loop, built-in RAG, bring-your-own-key, multi-provider (OpenAI / Claude / DeepSeek / Kimi). Self-hostable.
Overview of MindGeniusAI
What it is
MindGeniusAI is a self-hostable AI agent that reads PDFs and draws editable mind maps. It features a visible tool-calling loop, built-in RAG, and supports multiple providers (OpenAI, Claude, DeepSeek, Kimi). Users bring their own API key, and files and keys never leave the user's machine. The project ships as a single Docker image and is designed for privacy-conscious knowledge workers, self-hosters, and teams with sensitive documents.
Key features
- Self-hosted & private — runs as one Docker image; PDFs are chunked/embedded in memory, keys live in the browser, nothing written to server disk.
- Real agent, not a prompt wrapper — multi-step tool loop (Vercel AI SDK v5) that decides when to search docs, generate the map, and expand branches, each shown as a live tool card.
- Surgical edits — rename or modify specific nodes by ID without full re-render.
- Two-way canvas — manual edits (rename, add, drag, delete) are seen by the agent on the next message, enabling collaborative refinement.
- Reads your PDFs — attach one or more PDFs; chunk → embed → in-memory retrieval (~100 lines, no LangChain).
- Keyboard-first canvas — Tab for child, Enter for sibling, F2 rename, Del delete, ⌘Z undo, drag to re-parent.
- Command palette (⌘K) — fuzzy-search saved maps and uploaded docs.
Use cases
- Privacy-conscious knowledge workers who want to process sensitive documents locally.
- Self-hosters who prefer to run their own infrastructure.
- Teams with confidential documents (legal, research, internal specs) that cannot be uploaded to third-party cloud services.
- Anyone who needs an editable mind map generated by an AI agent with visible reasoning steps.
Getting started
bash pnpm install pnpm setup # pick a provider, paste a key → writes apps/server/.env pnpm dev # web on :5173, api on :3000
License and pricing
Business Source License 1.1. Free for personal, academic, research, and non-profit use. Commercial use requires a license — contact [email protected]. Each version converts to Apache-2.0 four years after release (Change Date: 2030-06-29).
Based on the project's public README and repository metadata.