Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/john-data-chen/hermes-agent-backup/heartmulanpx skills add john-data-chen/hermes-agent-backup --skill heartmulagit clone --depth 1 https://github.com/john-data-chen/hermes-agent-backupWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/john-data-chen/hermes-agent-backup/heartmula)<a href="https://agentmods.dev/skills/john-data-chen/hermes-agent-backup/heartmula"><img src="https://agentmods.dev/badge/skills/john-data-chen/hermes-agent-backup/heartmula.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00017 | $0.01752 |
| Opus 5 | $0.00009 | $0.00876 |
| Sonnet 5 | $0.00003 | $0.00350 |
| Haiku 4.5 | $0.00002 | $0.00175 |
Grade A, and why
heartmula scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
95% identical to heartmula — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HeartMuLa - Open-Source Music Generation
Overview
HeartMuLa is a family of open-source music foundation models (Apache-2.0) that generates music conditioned on lyrics and tags, with multilingual support. Generates full songs from lyrics + tags. Comparable to Suno for open-source. Includes:
- HeartMuLa - Music language model (3B/7B) for generation from lyrics + tags
- HeartCodec - 12.5Hz music codec for high-fidelity audio reconstruction
- HeartTranscriptor - Whisper-based lyrics transcription
- HeartCLAP - Audio-text alignment model
When to Use
- User wants to generate music/songs from text descriptions
- User wants an open-source Suno alternative
- User wants local/offline music generation
- User asks about HeartMuLa, heartlib, or AI music generation
Hardware Requirements
- Minimum: 8GB VRAM with
--lazy_load true(loads/unloads models sequentially) - Recommended: 16GB+ VRAM for comfortable single-GPU usage
- Multi-GPU: Use
--mula_device cuda:0 --codec_device cuda:1to split across GPUs - 3B model with lazy_load peaks at ~6.2GB VRAM
Installation Steps
1. Clone Repository
cd ~/ # or desired directory
git clone https://github.com/HeartMuLa/heartlib.git
cd heartlib
2. Create Virtual Environment (Python 3.10 required)
uv venv --python 3.10 .venv
. .venv/bin/activate
uv pip install -e .
3. Fix Dependency Compatibility Issues
IMPORTANT: As of Feb 2026, the pinned dependencies have conflicts with newer packages. Apply these fixes:
# Upgrade datasets (old version incompatible with current pyarrow)
uv pip install --upgrade datasets
# Upgrade transformers (needed for huggingface-hub 1.x compatibility)
uv pip install --upgrade transformers
4. Patch Source Code (Required for transformers 5.x)
Patch 1 - RoPE cache fix in src/heartlib/heartmula/modeling_heartmula.py:
In the setup_caches method of the HeartMuLa class, add RoPE reinitialization after the reset_caches try/except block and before the with device: block:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 172 lines · 17 tokens per session scan A d6f8322ba9ab
heartmula is a skill published in the GitHub repository john-data-chen/hermes-agent-backup (2 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,752 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to heartmula, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
hive.image-generation
Required before calling imagegenerate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2…
media-gen
Generate or edit images, videos, or audio (text-to-speech) in the current task. Use whenever the user asks to create/generate/produce or edit/modify a picture / image / illustration / cover / poster / icon / artwork, a video / clip / animation, or speech / voiceover / narration / TTS — e.g. generate image, draw…
veo-generator
Render a scripted video project into mp4 clips with the Google Veo 3.1 API. Reads a project's shot package (shots/.md), one clip per camera cut, reusing each shot's prompt and sketch — world anchor only with --with-reference, seed unless --no-seed. Use on "render the Veo video for ", "generate the videos from the shot…
nano-banana-imagegen
Generate and edit images using Google Gemini image models via the nano-banana CLI. Use when the user asks to create, generate, make, or edit images with AI. Supports text-to-image, image editing, style transfer, and multi-image composition. Trigger on requests like "create an image", "generate a picture", "make me a…
video-transcription
Transcribe video and audio files to SRT subtitle format with speaker diarization using the Soniox API. Use when the user wants to transcribe meeting recordings, videos, or audio files. Supports MKV, MP4, MOV, M4A, and MP3 files. Triggers on "/transcribe", "transcribe my meetings", "transcribe videos in /Movies"…
veo-showreel-production-kit
Turn a video timeline + voiceover into a reproducible, sliceable Veo 3.1 prompt package with a consistency anchor and AI storyboard sketches.