### Deterministic Music Theory for Claude, Cursor, and Autonomous AI Agents
Large Language Models (LLMs) frequently hallucinate music theory, leading to incorrect notes, false Roman numerals, and broken voice leading. **THIRI** solves this by providing a deterministic, mathematical music-theory engine (pitch-class-set theory over ℤ/12) directly to your AI.
It gives AI assistants precise, reproducible harmonic reasoning in milliseconds, allowing them to write correct musical scores, analyze progressions, and generate playable arrangements.
#### 🎷 Key Features:
* **Chord Analysis (`analyze_chord`):** Parse any symbol (e.g., `Cmaj7/E`, `G7#11`) to retrieve root, quality, intervals, Roman numerals, and diatonic or chromatic harmonic functions.
* **Note Resolution (`resolve_chord`):** Resolve chord symbols to spelled notes (enharmonically correct), frequencies (Hz), MIDI numbers, and scale recommendations.
* **Voicing Engine (`generate_voicing`):** Generate instrument-ready voicings (rootless, shell, triad, pad, drop-2, drop-3) and calculate voice-leading scores for transitions.
* **Reharmonization (`reharmonize`):** Substitute progressions using classic jazz techniques, including Tritone Substitution, ii-V Insertion, Modal Interchange, Coltrane Changes, and Backdoor cadences.
*Ideal for developers building AI music assistants, digital audio workstation (DAW) agents, educational theory tools, and automated composition workflows.*