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 skills add MilkyWay008/Hermes-OTG --skill heartmulagit clone --depth 1 https://github.com/MilkyWay008/Hermes-OTGWrote 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/milkyway008/hermes-otg/heartmula)<a href="https://agentmods.dev/skills/milkyway008/hermes-otg/heartmula"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/heartmula/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/milkyway008/hermes-otg/heartmula"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/heartmula.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00017 | $0.01761 |
| Opus 5 | $0.00009 | $0.00881 |
| Sonnet 5 | $0.00003 | $0.00352 |
| Haiku 4.5 | $0.00002 | $0.00176 |
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 11d 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
100% identical to heartmula — 2 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.
- 11d ago First seen · 172 lines · 17 tokens per session scan A 5ee5f48a6963
heartmula is a skill published in the GitHub repository MilkyWay008/Hermes-OTG (15 stars, last pushed 27d ago), licensed MIT. It adds 17 tokens to every session and 1,761 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to heartmula, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
youtube-full
Use when YouTube is or could be relevant — even if not mentioned: pasted video/channel/playlist links, video IDs, @handles, creator lookups, video summaries, quotes, translations, topic research, tutorials, talks, lectures, expert discussions, product reviews, how-to guides, new product announcements, first looks, or…
video-transcript
Use when video content needs to be extracted as text: pasted YouTube links or IDs, requests to transcribe, summarize, quote, translate, convert video to text, or extract information from video content. Also use when a user shares a video URL without explanation and wants to know what it says. Not for uploads or…
moxiangtongxiu-perspective
A Chinese-language creative-writing guide built around character-led stories, interwoven plotlines, memorable dialogue, ensemble casts, and emotional contrasts. It is presented as a perspective associated with the author Mo Xiang Tong Xiu.
tangjiasanshao-perspective
A Chinese web-fiction writing approach centered on daily serialization, character power progression, structured fantasy systems, dramatic pacing, and long-running story worlds. It is framed around the style and working methods associated with Tang Jia San Shao.
vid-motion-graphics
Generates motion graphics videos (MP4) from a content brief. Multi-scene HTML/CSS animations rendered frame-by-frame in headless Chromium via Playwright, assembled with FFmpeg. 1080×1080 default, 16:9 (1920×1080) and 9:16 (1080×1920) supported. 5 style presets. Trigger when user says "create a video", "motion…
blog-cover-generator
Use when the user asks to generate a blog cover image, thumbnail, or article header. Automatically uses modern typography, brand logos, and Google Search grounding to create beautiful 16:9 images with Gemini 3.1 Flash Image Preview.