AwsmAudio – a WebAudio editor with native MCP
Hey y'all, So - the main idea of this is to make a WebAudio synthesis/sequencer tool which humans can use via the UI, but where the big unlock is for agents to drive with MCP It's semi decent as "make a groovy jazz track", especially for retro sounds - but the real use case is more like "make a jetpack whoosh effect I can control via code at runtime - where the sound changes based on character health or how much fuel is left" In other words, the target audience is not musicians (except maybe of the Max/MSP sort), but more like creative coders who want to shape the sound iteratively…
What it does
In the maker’s words, at launch
Hey y'all, So - the main idea of this is to make a WebAudio synthesis/sequencer tool which humans can use via the UI, but where the big unlock is for agents to drive with MCP It's semi decent as "make a groovy jazz track", especially for retro sounds - but the real use case is more like "make a jetpack whoosh effect I can control via code at runtime - where the sound changes based on character health or how much fuel is left" In other words, the target audience is not musicians (except maybe of the Max/MSP sort), but more like creative coders who want to shape the sound iteratively with an agent, and then use and _drive_ in in a game/simulation. Fwiw I think this approach is going to be more and more... and I'm working on a renderer/editor tool too (will share separately when ready). What I mean is, there's a lot of "block box" AI tooling out there, and a lot of "add MCP to existing tools", but building new tools where humans get one experience and MCP exposes another layer really just for agents.. I think that's powerful. Most if it is just mapping the WebAudio primitives to a UI and MCP server - but the AudioWorklet is a bit more interesting in that it expects a WASM file of a particular shape, and then uses that to expose the parameters in the UI and hook in as a Digital Signal Processor. That's the kind of thing that is nice for humans, but too convoluted to be usable in a UI, and agents can use super easily. As of right now, there's no hosting - so the MCP server is local as is project save/loading. Repo: https://github.com/awsm-fun/awsm-audio Crates: https://crates.io/search?q=awsm-audio
Does the same job
all alternatives →- T3TB-303 Synth, Drum Machine and Sequencer in Web Audio2016 · errozero.co.uk · ▲238
- T1TR-101 – A drum synth/sequencer made with Vue and the web audio API2017 · inverted3.gitlab.io · ▲105
- WDWeb DSP audio editor2018 · dsp.audio · ▲133
- BWBitMidi – Wayback machine for old-school MIDI files2018 · bitmidi.com · ▲168
- MSMIDI.space – WebMIDI and Audio Mashup for Finger Drumming2015 · midi.space · ▲50
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 2d ago · opentrailpaper.com
Launched alongside, June 2026
the whole month →
Fundraisly▲1,544AI fundraising agent that finds investors and books meetings
AI · Jun 2026 · fundraisly.com
- H6Homebrew 6.0.0▲1,481
Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!
Dev tools · Jun 2026 · brew.sh
- PU
hope you enjoy
Life & fun · Jun 2026 · vorpus.github.io
- IM
Life & fun · Jun 2026 · hackernewstrends.com