# Memorwise

> Self-hosted NotebookLM alternative for document chat with any LLM. Drop in files/links — local RAG Q&A, knowledge graphs, flashcards, quizzes, audio. One command.

- **Category:** AI Chat
- **Licence:** MIT
- **Open source:** oss
- **Languages:** Typescript
- **Platforms:** Node.js, Build from Source
- **Tags:** SQLite, Mcp Server, Local First, LLM, Rag, Anthropic, Gemini, Openai, Ollama, Vector Search, Knowledge Graph, Typescript, Next.js, Open Source, AI, Self Hosted, Embeddings, Whisper, Tesseract, Document chat, Flashcards, Lancedb, Kokoro tts, Notebooklm, Study Tools, Notebooklm Alternative, Audio Overview

## Description

Memorwise is an open-source, local-first application for chatting with and studying from your documents. You provide various file types and links, and the software processes them on your machine using an embedded database and vector store. It supports eight LLM providers including Ollama, LM Studio, OpenAI, Anthropic, Gemini, Groq, Mistral, and OpenRouter, with per-task model selection for chat, embeddings, transcription, and text-to-speech. Capabilities include question-answering with source citations, AI-extracted knowledge graphs showing concept connections, auto-generated flashcards and quizzes, podcast-style audio overviews via local Kokoro TTS or OpenAI, a Markdown notes editor with backlinks, and semantic search across notebooks. Installation is a single command (npx memorwise) requiring Node.js 22.13+ and git, running on http://localhost:4747. Optional dependencies include ffmpeg for video transcription and espeak-ng for local TTS. An MCP server exposes 35 tools for AI coding assistants like Claude Code and Cursor. All data remains in a local directory with configurable location via MEMORWISE_DATA_DIR. The project is licensed MIT and built with Next.js 15, React 19, TypeScript, and Tailwind CSS v4.

## Links

- [Homepage](https://github.com/robzilla1738/Memorwise)
- [Website](https://memorwise.com)
- [GitHub Repository](https://github.com/robzilla1738/Memorwise)

---
Source: https://selfhost.directory/project/memorwise