ISMAIL

A DAW for AI agents.
It can't hear, so it reads.

The agent writes notes, instruments and effects as text, renders, and reads the audio back as text: levels per bar, drum lanes, piano rolls, chords, song structure. Every song on this page was composed, sound-designed and mixed by an AI agent through ismail's tools, with a human listening and giving notes.

1. write

# beat, pitch, length, velocity
notes_write track=bass bar=17 repeat=8
  notes="0 A1 0.5 110; 0.75 A1 0.25 90"
# a drum lane as 16th steps
pattern_write track=kick bar=17
  lanes='{"C1": "X...x.....X.x..."}'

2. render

render out=final mp3=also
rendered 78.8s -> renders/final.mp3
master: -11.8 LUFS, peak -0.3 dBFS
  kick   peak  -2.4 rms -20.0 dB
  bass   peak  -2.6 rms -16.3 dB
  pad    peak  -9.6 rms -25.4 dB
  master fx 0: max gain reduction -5.9 dB

3. read it back


      

Listen

Under each song is the text the agent used to judge it: the arrangement map (one character per bar, 9 = loudest, rows per frequency band, the bass note and the sections it found) and a piano roll of one part. Press play and the playhead runs across the map; click the map to jump to a bar.

On YouTube

Luigi Manson: the Luigi's Mansion theme as dubstep, made with ismail. One bass voice plays the hook, and the note velocity picks each hit's articulation: a vowel sweep, a wub, a screech, a talk word ("Mario?").

Luigi Manson (fan remix). Open on YouTube

How it works

About 70 tools behind one MCP server (or a CLI). The agent never needs ears; it needs readings it can trust.

Everything goes in as text

Notes, drum patterns, synth patches, effect chains, buses, automation. Instruments range from subtractive synths and drum synths to samplers and voices written as Python (the piano on this page is one: measured partials, no samples).

Everything comes back as text

Tempo and grid, arrangement maps, levels and bands per bar, drum lanes as step strings, piano rolls, chords, timbre, vowels of a voice. A spectrogram PNG exists, but nothing needs it.

It can match a reference

Give it a recording: it finds the grid, separates stems, transcribes only notes that repeat (echoes and bleed drop out), fits instruments to extracted sounds, and scores every draft against the reference's own variation, with drill-down to a single bar.

It comes with a skill

An agent skill teaches the workflow: plan the piece before writing notes, check every render with the analysis tools, and trust baseline-scored comparisons over a hunch.

A studio, not a music generator

Suno and similar services are models that turn a prompt into audio. ismail is the opposite kind of thing: a set of tools your own agent uses to write the song as notes, sounds and code, render it, read what came out, and edit. Here is how that compares with a music generator, and with driving a classic DAW like Ableton or FL Studio.

ismail + your agentSuno (music generator)Ableton, FL Studio
What makes the music Your agent's own reasoning: harmony, rhythm, sound design and the math behind each synth A trained model that generates audio from a prompt You, with an agent at most pressing buttons through a bridge
How you change it Edit one note, one patch, one bar, one fader; re-render in seconds; everything else stays exactly as it was Regenerate, extend or replace sections of generated audio; stems and a browser studio on paid plans Full manual control, by hand
What the agent can perceive Every render comes back as text: levels per bar, drum lanes, piano rolls, chords, structure, scored comparisons Nothing to perceive: you listen and write a new prompt Usually nothing: the agent turns knobs without hearing the result
Sounds Anything the agent can describe as code: synths, drum synths, samplers, voices written in Python, speech; any sound becomes an instrument The palette the model learned The plugins you own
The song is A project file and a build script: git history, diffs, branches and code review for a track Audio files Binary project files
Runs On your machine, open source (MIT), no content filter, no music subscription (you bring the agent: Claude Code, Cursor or any MCP client) A hosted service with plans; the free plan is non-commercial Paid licenses, closed source
Gets better when The model driving it gets better: the same prompt, a stronger model, a better song The vendor ships a new model You get better
Extending it Any agent or person can add an instrument, an effect or a way to listen, in a few lines of Python Limited to what the service offers (including custom models trained on your own audio) Plugin SDKs around a closed core

What Suno does better

  • Realistic sung vocals with lyrics. ismail has formant voices, vocoders and speech, not a singer.
  • A full, polished song from one sentence in under a minute. An agent writing a song in ismail takes longer and needs good direction.
  • Genre sound learned from a huge amount of recorded music. Here every sound has to be designed.
  • Nothing to install.

Why not just drive Ableton or FL Studio?

They were designed before AI agents, for a person with ears and a mouse. Bridges and scripting let an agent press their buttons, but the instruments, channels and arrangement aren't laid out as text an agent can reason about, and the agent still can't hear what it did.

ismail starts from the other end: everything an agent needs to write and to perceive is compact text, and renders are fast. Its first working version was written by an AI agent in about a day, which is the point: if something is missing, your agent can add it.

Local does not mean copyright-free: a remix of someone else's melody is still their melody. What changes is that nothing here is generated by a model trained on other people's recordings; the notes and sounds are whatever your agent writes. Suno plan details as of 2026 (Suno).

Get started

Python 3.10+. Works with Claude Code, Cursor or any MCP client, or straight from the shell.

Install and connect

pip install git+https://github.com/newsbubbles/ismail
claude mcp add -s user ismail -- python -m ismail.mcp_server

Ask for a song

"make a 16 bar lo-fi loop in D minor
 in songs/demo and render an mp3"

Skill install, Cursor setup and the full tool list: README.