Bionic / LM Studio

Run Producer Pal fully offline with Bionic / LM Studio, a free app that downloads and runs AI models on your own computer and has its own chat window. Prefer Producer Pal's chat window? See Bionic / LM Studio in the Built-in Chat UI.

Needs a powerful computer and some patience

Local AI needs an Apple Silicon Mac with lots of memory, or a PC with a strong Nvidia graphics card (see Running Locally). It takes more setup than the online options, and it's slower and less smart.

This guide is for Bionic. The older LM Studio app also works: follow LM Studio's own MCP setup and use the same settings.

Requirements

Download Max for Live DeviceProducer_Pal.amxd — for Ableton Live

• Ableton Live 12.3+ with Max for Live. Live 12.4 or later is recommended. On Live 12.3 these don't work:

  • writing clip automation (reading and clearing it still work)
  • loading a sample into Simpler
  • the Library tool (searching your library and listing plug-ins)
  • finding a preset by name outside a device's own presets (packs' drum kits, Sounds racks, custom folders)
  • opening a plug-in's editor window

  Use the version of Max bundled with Live, or make sure your standalone Max is up to date.

• Bionic

• Node.js 20+

Bionic is free, and so is running models on your computer. You don't need an LM Studio account.

Installation Steps

No need to install the Producer Pal device yourself: in the last step, the AI sets up Live for you.

Or install the device yourself

Download Producer_Pal.amxd, the Producer Pal Max for Live device.

Open User Library (under Places) in Live's browser, go to Presets → MIDI Effects → Max MIDI Effect, and drag Producer_Pal.amxd into that folder:

Drag it from the Max MIDI Effect folder onto a MIDI track:

It should display "Producer Pal Running" or something isn't working.

Then finish the installation: click Finish installation… on the device (or Open Chat UI, then Settings → Installation), and click Install there to add the remote script (clip automation, undo, plug-ins).

Restart Live, then choose Producer Pal as a Control Surface in Settings → Tempo & MIDI, with Input and Output left as None.

More in Finish the Installation.

1. Install a Compatible Model

Download a model in Bionic under Settings → Explore, such as a recent version of Qwen, Gemma, Mistral, or Nemotron. If your computer can handle it, use the larger variants of a model.

It has to support tools. Your downloaded models are listed under Settings → Library, where a hammer icon marks the ones that do:

2. Add Producer Pal to Bionic

Go to Settings → Connected Apps and click "+ Add custom MCP" under Manual MCP server setup:

Fill in:

• Name: Producer Pal
• Connection: On this computer
• Command: npx
• Turn on Show advanced options, then use + Add argument to add -y and producer-pal@latest as two separate arguments

This way Bionic can start before Live, and it tells you when Live or the device isn't running.

Click Add MCP. Producer Pal should show as connected, with its tools ready:

Restart Bionic after changing MCP settings

Adding a server or editing its arguments may not take effect until you restart the app.

3. Start Using Producer Pal

Bionic works in a project tied to a local folder, so create one with New Project before starting a conversation. An empty folder is recommended for Producer Pal sessions. Feel free to put reference documents in it, such as common workflow instructions or details of your preferred musical style and production techniques.

With Live open, start a conversation and say "connect to ableton".

The first time, the AI sets up Live for you:

1. It installs the Producer Pal remote script.

2. Restart Live, then choose Producer Pal as a Control Surface in Settings → Tempo & MIDI, with Input and Output left as None.

3. Tell the AI when you're done. It installs the Producer Pal device and adds it to your Live Set (it asks first).

4. Tune It for Your Model (Recommended)

Do this only after step 3, once the device is in your Live Set. Small model mode hides the tool that sets Producer Pal up.

Bionic has no tool picker, so the MCP server's arguments are the only place to narrow what Producer Pal offers — and small models do much better with a short tool list. The same arguments also switch on the settings that make Producer Pal easier for a local model to drive:

• --small-model-mode — a smaller, simpler interface built for local models
• --notation stark — a literal type: content format with event-based drum hits, which small models handle better than the default bar|beat text
• --tools core,clip,track — a focused toolset, which also shrinks the skills the model reads on connect.

Edit the server under Settings → Connected Apps and add them as arguments, one field each — a flag and its value are two separate arguments:

--tools keeps only what you list; --disable-tools drops what you list. Both take tool names (read-clip or ppal-read-clip) and group names: core, session, actions, live-set, track, scene, clip, device, advanced, and read-only. Run npx producer-pal@latest --list-tools to print the groups plus the tools the running device currently offers.

Withholding a tool also drops the part of the Producer Pal Skills that teaches it, so you stop paying for the tool's schema and its guidance in every conversation. --tools read-only cuts the skills text by more than half.

Unlike the other flags, this one is per client: the Chat UI and your other MCP clients keep the full toolset. ppal-connect is always kept, since it is how the AI connects and receives the skills.

One wrinkle with --tools: it keeps what you list by withholding everything else, and "everything else" is the tool list this copy of npx producer-pal knows, so a tool added in a newer Producer Pal stays enabled until you update. --disable-tools names tools directly, so it can withhold a newer tool even from an older copy; only its group names are limited to the ones above.

These flags apply to Bionic only. To set them for the whole device instead (including the built-in chat UI and other connected clients), use Producer Pal's "Setup" tab:

Check It Works

Once connected, the AI confirms it can see your Live Set. Try a first request that doesn't change anything:

What tracks are in my Live Set?

It should list your tracks. If it can't connect or gets something wrong, see Troubleshooting below.

Local Model Tips

• Set the context length to 16k (16000) or higher in the model's settings. This is how much the AI can keep in mind at once. About 8k is enough to connect and send a few messages. Higher is slower, so find the balance.
• Keep it simple: start from an empty Live Set and short material, like MIDI clips of 4 bars or less. Small models are told to delete and start over rather than make edits (other than simple additions).
• When it goes wrong, back up. Delete the last messages or edit your last message and try again, instead of trying to correct the AI.
• Close apps you don't need so the model gets more of your computer.

Advanced Tips

• Skip npx by setting Connection to Web address with the URL http://localhost:3350/mcp. Live and the device must then be running before Bionic connects (install the device yourself), and it won't reconnect on its own.
• Add tools back to --tools when you miss features. Every tool you add takes up room on every conversation.
• Follow-up messages are often faster than the first: the model reuses work from earlier turns.
• Run Ableton Live on a different computer on your local network.
• With a GGUF model, try the experimental Flash Attention setting and set the K/V caches' quantization to Q8 or Q4.
• To go further, customize Producer Pal's Skills for your model. If you find a setup that works well, share it in GitHub Discussions.

Troubleshooting

If it doesn't work, see the Troubleshooting Guide.