Minne

A graph-powered personal knowledge base that makes storing easy.

Capture content effortlessly, let AI discover connections, and explore your knowledge visually. Self-hosted and privacy-focused.

Try It

Live Demo — Read-only demo deployment

Quick Start

git clone https://github.com/perstarkse/minne.git
cd minne

# Set your OpenAI API key in docker-compose.yml, then:
docker compose up -d

# Open http://localhost:3000

Or with Nix (with environment variables set):

nix run 'github:perstarkse/minne#main'

Pre-built binaries for Windows, macOS, and Linux are available on the Releases page.

Features

• Fast — Rust backend with server-side rendering and HTMX for snappy interactions
• Search & Chat — Search or use conversational AI to find and reason about content
• Knowledge Graph — Visual exploration with automatic or manual relationship curation
• Hybrid Retrieval — Vector similarity + full-text for relevant results
• Multi-Format — Ingest text, URLs, PDFs, audio, and images
• Self-Hosted — Your data, your server, any OpenAI-compatible API

Documentation

Guide	Description
Installation	Docker, Nix, binaries, source builds
Configuration	Environment variables, config.yaml, AI setup
Features	Search, Chat, Graph, Reranking, Ingestion
Architecture	Tech stack, crate structure, data flow
Vision	Philosophy, roadmap, related projects

Tech Stack

Rust • Axum • HTMX • SurrealDB • FastEmbed

Contributing

Feature requests and contributions welcome. See Vision for roadmap.

License

AGPL-3.0