mirror of
https://github.com/hanzoai/cdn.git
synced 2026-11-02 21:02:16 +00:00
zeekayandHanzo Dev
edabf3842c
The Market read plane is files and nothing else. This makes that actually true
and actually deployable.
Catalog: was 10 mock "zoo-eco-agent" placeholders + 5 mock tools, which every
app would have shown to every user. Now generated from the curated flatfile
catalog (hanzoai/store data/{agents,tools}) -> 23 agents + 179 tools, each with
its own detail document. Drops purchases.json: per-user state has no business
on a public CDN. Strips upstream icon URLs, which are expired presigned R2 links
that carry an AWS credential + signature in the query string.
Versioning: index.json gains `schema` (breaking-shape gate, so a client that
does not recognise it keeps its bundle) and a `version` that is a content digest
over every served document. It changes iff what we serve changes, which is what
makes a deploy checkable rather than hopeful.
One writer: gen-market.py -> market.py with `gen` and `check`. It emits the CDN
documents AND each app's offline bundle, so the two cannot disagree about the
schema; `check` re-derives the digest and validates counts, ids, dangling
featured references and per-tool details, with no network and no other checkout.
Deploy: upload, then purge the Cloudflare edge for exactly the URLs written,
then verify the live manifest matches the repo and fail if it does not. Also
resolves wrangler once instead of re-resolving it per object.
CI: hanzo.yml + a 7-line cicd.yml importing hanzoai/ci. Static assets, so no
images:/deploy: — test: is the gate.
Co-authored-by: Hanzo Dev <[email protected]>
47 lines
2.9 KiB
JSON
47 lines
2.9 KiB
JSON
{
|
|
"author": "hanzo.ai",
|
|
"category": {
|
|
"description": "",
|
|
"examples": "",
|
|
"id": "entertainment",
|
|
"name": "Entertainment"
|
|
},
|
|
"changelog": "",
|
|
"created_at": "2025-10-12T17:03:11.808Z",
|
|
"description": "This tool functions as a personal soundscape generator, creating single ambient audio experiences tailored to your specific prompts. By leveraging a Large Language Model (LLM), it intelligently selects and mixes sounds from a library to produce a unique MP3 file that matches the mood or environment you describe.\n\n(Note: To build longer evolving sound journeys, use the tool 'ambient sound journey composer', which uses the present tool under the hood.)\n\n### How to Use the Tool:\n\nThis tool offers a straightforward, step-by-step process for creating your ideal ambient soundscape:\n\n1. **Download the Sound Library**: Before you can generate any soundscapes, you must first download the necessary audio assets. To do this, simply run the tool with the `download_assets` option set to `True`. This will fetch the default sound library from a GitHub repository and store it on your local machine. The tool supports .mp3 and .wav sound files.\n\n2. **Customize with Your Own Sounds (Optional)**: You have the creative freedom to expand the sound library. To add your own audio, just place any MP3 or WAV files into the designated `assets_folder`. You can also create subfolders to organize your sounds by category. For best results, use only a 2 level depth (categories, subcategories, no more). The tool will automatically detect and integrate these new files, making them available for your soundscapes.\n\n3. **Generate Your Soundscape**: Once your sound library is ready, you can start creating. Provide a descriptive `prompt` detailing the type of ambient sound you want (e.g., \"a peaceful forest with a gentle stream and distant birds\"). The tool will then generate a custom MP3 file based on your description.\n\n4. **Explore Your Sound Options (Optional)**: If you're unsure what sounds are available or want to get ideas for your prompts, you can set the `show_available_sounds` option to `True`. This will provide a complete list of all the sounds in your library, including any you've added yourself, without generating an audio file.",
|
|
"downloads": 0,
|
|
"icon_url": "",
|
|
"id": "ambient-sound-composer",
|
|
"install_command": "",
|
|
"license": "MIT",
|
|
"mcp_config": {
|
|
"args": [
|
|
"local:::__official_shinkai:::ambient_sound_composer"
|
|
],
|
|
"command": "any",
|
|
"env": {}
|
|
},
|
|
"name": "Ambient Sound Composer",
|
|
"operating_system": [
|
|
"linux",
|
|
"macos",
|
|
"windows"
|
|
],
|
|
"path": "/tools/ambient-sound-composer",
|
|
"price": 0,
|
|
"readme": "",
|
|
"repository": "github.com/hanzoai/tools",
|
|
"router_key": "@hanzo/ambient-sound-composer",
|
|
"runner": "any",
|
|
"screenshots": [],
|
|
"tags": [
|
|
"soundscape",
|
|
"ambient",
|
|
"sound",
|
|
"relax"
|
|
],
|
|
"type": "Tool",
|
|
"updated_at": "2025-10-12T17:03:11.808Z",
|
|
"version": "1.0.0"
|
|
}
|