embabel/impromptu

Classical music exploration chatbot built using Embabel and Neo4j

What's novel

Classical music exploration chatbot built using Embabel and Neo4j

Code Analysis

22 files read · 6 rounds

A classical music discovery chatbot that uses LLM-powered agents to plan concerts, find recordings on Spotify/YouTube, write program notes, and extract user preferences via DICE proposition extraction, all backed by a Neo4j graph+vector RAG store.

Strengths

Well-structured multi-agent architecture with clean separation between chat orchestration, concert assembly, program note writing, and platform integrations; the escalating entity resolver and artifact-capturing tool patterns show thoughtful engineering of LLM tool interactions.

Weaknesses

Heavy dependency on the Embabel Agent Framework (SNAPSHOT versions) means the core agent loop, DICE pipeline, and RAG engine are external — this project is primarily a domain-specific consumer rather than a self-contained system; test coverage appears thin relative to the 147 source files.

Score Breakdown

Innovation

5 (25%)

Craft

78 (35%)

Traction

28 (15%)

Scope

81 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+1

Concept Novelty+2

Craft

Ci+5

Tests+8

Polish+1

Releases+0

Has License+5

Code Quality+22

Readme Quality+15

Recent Activity+7

Structure Quality+5

Commit Consistency+5

Has Dependency Mgmt+5

Traction

Forks+6

Stars+12

Hn Points+0

Watchers+3

Early Traction+5

Devto Reactions+0

Community Contribs+2

Scope

Commits+8

Languages+8

Subsystems+5

Bloat Penalty+0

Completeness+7

Contributors+7

Authored Files+15

Readme Code Match+3

Architecture Depth+7

Implementation Depth+8

Evidence

Commits

215

Contributors

Files

255

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Java

Stars

Forks

License

Apache-2.0