# Extending Producer Pal Producer Pal is a stable core with open edges. The core does one thing: control Ableton Live, with the fewest tools and tokens it can manage. How the AI is instructed, what you drive it from, and whether there's an AI involved at all is up to you, without forking the repo or changing the core. ## Script Live over the REST API The [REST API](/guide/rest-api) exposes every tool over plain HTTP on your own machine. There's no AI in this path unless you add one. ```bash # Read the Live Set overview curl -X POST http://localhost:3350/api/tools/ppal-read-live-set \ -H 'Content-Type: application/json' -d '{}' # Set the tempo to 128 curl -X POST http://localhost:3350/api/tools/ppal-update-live-set \ -H 'Content-Type: application/json' -d '{"tempo": 128}' ``` You can: - **Build your own interface.** A local web page can drive Live: the whole REST API, straight from browser JavaScript. - **Use it without AI at all.** Generative scripts, batch edits across many clips, project scaffolding, reproducible test Sets. - **Put your own AI in front of it.** The API doesn't care which model. Use an agent framework, a local model, a notebook, whatever fits. The [`ppal-live-api`](/features/tools#ppal-live-api) tool goes lower, with direct access to the [Live Object Model](https://docs.cycling74.com/apiref/lom/) for reads and writes the specialized tools don't cover. It's off by default; see [Live API](/guide/rest-api#live-api). Zero-dependency [Node and Python sample scripts](/guide/rest-api#sample-scripts) are included to get you started. ## Drive it from a coding agent Producer Pal ships a portable [Agent Skill](/guide/skills), built on the `SKILL.md` convention shared by Claude Code, Codex CLI, and Gemini CLI. Drop the folder into your agent's skills directory and it can control Live through the REST API, no MCP client needed. A coding agent can write and run code against the API, iterate on a generative script while you listen, and change device settings mid-session: [notation](/features/midi-notation), [small model mode](/features#small-model-mode), [Direct Live API](/features/tools#ppal-live-api). MCP clients can only change those by changing settings on the device and starting a new conversation. [Companion skills](/guide/skills#companion-skills) build on that connection. **`ableton-audio-generator`** synthesizes audio from scratch with plain Node.js DSP (drum kits, Simpler samples, wavetables, reverb impulse responses, drones) and places it in Live. **`ableton-export-audio`** goes the other way: it renders the mix, a single track, or one Session clip to a file (**macOS only**, because Live exposes no render API, so this drives the Export dialog with AppleScript). **`ableton-analyze-audio`** hands that file to Google's Gemini for feedback on how it actually sounds (any platform, needs a `GEMINI_KEY`; it's one small script, so pointing it at a different audio-capable API is a short edit). None of these belong in Producer Pal. Driving another app's UI and calling an external API need a real runtime the Max for Live device doesn't have. The device could technically do DSP, but synthesis is open-ended enough that an agent writing real code beats any DSL Producer Pal would have to teach. [Set up the Agent Skill →](/guide/skills) ## Customize what the AI is told Shape how the AI uses the tools with text, not code. It all lives in `~/.producer-pal/` as plain Markdown you can edit, back up, and share, and you can edit it in the [context editor](/guide/context#the-context-editor). - **[Skills](/guide/customizing-skills)**: the instructions the AI gets when it connects. Override any fragment with your own text, or delete the parts you don't use so you stop paying for them every conversation. A fragment can also `@include` your own Markdown files, to add guidance the built-ins don't cover. - **[Global context](/guide/context#global)**: what you want in every Live Set, your genres, your habits, your rules. - **[Memory](/guide/context#memory)**: facts the AI records about you as you work, loaded on demand so a growing memory stays cheap. - **[Custom instructions](/guide/context#instructions)**: the system prompt for the built-in [Chat UI](/guide/chat-ui). (External clients bring their own.) If you can describe a workflow in plain language, you can change how the AI works. ## Choosing the right extension point | I want to… | Use | | ------------------------------------------------------- | -------------------------------------------------- | | Script Ableton Live without AI | [REST API](/guide/rest-api) | | Build my own interface for Live | [REST API](/guide/rest-api) | | Work from Claude Code, Codex CLI, or Gemini CLI | [Agent Skill](/guide/skills) | | Synthesize audio and land it in Live | [Companion skills](/guide/skills#companion-skills) | | Render a mixdown or stem (macOS only), or analyze a mix | [Companion skills](/guide/skills#companion-skills) | | Teach the AI a production technique | [Skills](/guide/customizing-skills) | | Tell the AI my preferences once, for good | [Global context](/guide/context#global) | | Cut what the AI costs per conversation | [Trim the skills](/guide/customizing-skills) | ## Ideas under consideration These aren't commitments, just what I'm thinking about after 2.1: - **Custom skills as first-class.** Today you extend the skills by overriding a fragment and `@include`-ing your own files. Registering a standalone skill (named, described, and loaded when it's relevant) is a natural next step. - **Personas.** [Presets](/guide/chat-ui#presets) already bundle a provider, model, tool set, and notation. Carrying their own context and skills too would make them a full switch of the AI's setup for a focused task. - **Workflows.** Fixed tool-call sequences the AI runs but doesn't improvise. 2.1 answered half the question with [subagents](/guide/chat-ui#subagents), which cover the delegation part; whether the fixed-sequence part is worth building, or is just a command-oriented skill, is still undecided. Have an opinion on any of these? [GitHub Discussions](https://github.com/adamjmurray/producer-pal/discussions) or [Discord](https://discord.gg/rmU3DSzgwH). ## Stable core The core repo won't change much after 2.0, and that's on purpose. Extensions don't break when the core doesn't move. Starting with 2.0, breaking changes need at least a minor version bump (2.1, 3.0); patch releases stay backward-compatible. Core work continues on bug fixes, new Live API features as they land, and efficiency, since cost matters whether you're on a local model, a subscription, or pay-as-you-go. All through small improvements, not rewrites. ## Contributing back If you find tweaks to the default skills or tool and parameter descriptions that make the AI behave better, send a pull request. Improvements to the built-ins reach everyone. A few areas I'm especially interested in: - **Skills and chat system instructions**: changes to the built-in Producer Pal Skills or the Chat UI system instructions, especially ones backed by experiments that show better behavior. - **Coding-agent skills**: more [Agent Skill](/guide/skills) examples for other workflows and agents. I'm happy to feature good ones on this site. - **MIDI notation and transforms**: experiments with other notation systems, and additions to the [transforms](/features/midi-notation#transforms) syntax. Ask first so we can agree on the grammar direction. Changes like these land best with [evals](https://github.com/adamjmurray/producer-pal/blob/main/evals/README.md) that show they help, ideally on both large and small models, since a prompt tweak that helps a big model can hurt a small local one. The toolset itself has stabilized, so changing a tool or adding one takes some convincing. Ask first. The [contributing guide](https://github.com/adamjmurray/producer-pal/blob/main/CONTRIBUTING.md) covers the strict code-quality checks (they're there to fight AI slop, not to gatekeep) and how to work with them. Questions, or an extension to show off? [GitHub Discussions](https://github.com/adamjmurray/producer-pal/discussions) or [Discord](https://discord.gg/rmU3DSzgwH).