NeptuneHub/AudioMuse-AI

AudioMuse-AI uses sonic analysis to rediscover forgotten songs, uncover hidden connections in your music library, and generate intelligent playlists for Navidrome, Jellyfin, LMS, Lyrion, Emby and Plex: no metadata or external services required.

What it solves

AudioMuse-AI is a self-hosted tool designed to help users rediscover forgotten songs in their music libraries and create playlists based on the actual sound of the music rather than relying on metadata or external APIs. It solves the problem of fragmented music collections across multiple servers and the limitation of traditional search and organization tools that depend on tags.

How it works

The system performs a sonic analysis of the music library to create a "sonic fingerprint" for each track. It uses this analysis to group similar songs (clustering) and map them visually in a 2D space. It integrates with popular self-hosted music servers like Navidrome, Jellyfin, Plex, and Emby to analyze tracks and export playlists. It can also analyze short audio clips (20 seconds) to find matching songs in the library.

Who it’s for

Music collectors and homelab enthusiasts who self-host their own music servers and want a more intuitive, AI-driven way to explore, organize, and search their music collection without relying on external services.

Highlights

  • Multi-Server Integration: Connects multiple media servers (Navidrome, Jellyfin, LMS, Lyrion, Emby, Plex) to a single deployment with built-in duplicate detection.
  • Sonic Clustering: Automatically groups sonically similar songs into genre-defying playlists.
  • Music Map: A visual 2D map for exploring the music collection based on sound.
  • Advanced Search: Supports text search for mood, instruments, and genre, as well as lyrics search across 72 languages.
  • Search by Recording: Find songs in the library using a 20-second audio clip or recording.
  • Song Alchemy: Mix and curate playlists by adding or subtracting tracks to refine a specific vibe.
  • Song Paths: Finds bridging tracks to create a seamless sonic transition between two songs.

Related

  • Project
    NeptuneHub/AudioMuse-AI-NV-plugin

    A Navidrome plugin that connects to the AudioMuse-AI engine to provide AI-powered features like automatic song mixes, artist similarity, and discovery tools directly within your music player.

  • Project
    Blueturboguy07/cue

    An open-source AI copilot that floats over your screen and remains invisible during screen shares, providing real-time assistance for meetings and coding.

  • Project
    timoncool/ACE-Step-Studio

    A desktop studio for ACE-Step 1.5 that enables local generation of full songs with vocals, featuring integrated LoRA training, stem separation, and MIDI tools.

  • Project
    coulsontl/ai-toolbox

    A cross-platform desktop application that provides a unified, visual interface to manage configurations, sessions, and plugins for various AI coding assistants and CLI tools.

  • Project
    luoguoxiong/aipack

    aipack is a TypeScript‑first, lightweight AI‑agent framework. It includes its own runtime, a Tapable‑based plugin system, and built‑in adapters for 13+ LLM providers. Features include streaming vs. batch execution, persistent session storage, permission‑based tool approval, hybrid BM25 + vector long‑term memory, five‑stage context compression, multi‑agent orchestration (graph, pipeline, router, debate, map‑reduce), two‑way MCP integration, full observability (metrics, dashboard), and an offline evaluation suite. The project ships a CLI assistant, a library for embedding in apps, and example apps demonstrating real‑world use cases.