Livepilot

██╗     ██╗██╗   ██╗███████╗██████╗ ██╗██╗      ██████╗ ████████╗██║     ██║██║   ██║██╔════╝██╔══██╗██║██║     ██╔═══██╗╚══██╔══╝██║     ██║██║   ██║█████╗  ██████╔╝██║██║     ██║   ██║   ██║██║     ██║╚██╗ ██╔╝██╔══╝  ██╔═══╝ ██║██║     ██║   ██║   ██║███████╗██║ ╚████╔╝ ███████╗██║     ██║███████╗╚██████╔╝   ██║╚══════╝╚═╝  ╚═══╝  ╚══════╝╚═╝     ╚═╝╚══════╝ ╚═════╝    ╚═╝

[CI] [npm version] [npm downloads] [License] [Latest Release]

Make the change. Hear what happened. Keep what works.
LivePilot connects an AI client to Ableton Live 12. Sketch ideas, edit the set, compare versions, and learn from the choices you keep.

474 tools · 57 domains · macOS + Windows

[!NOTE] LivePilot works with any MCP client, including Claude Code, Claude Desktop, Codex, Cursor, VS Code, and Windsurf. Changes inside the Live set use Ableton's undo stack. Downloads, saved memory, library scans, and installer changes happen outside the set and cannot be undone from Ableton.

[!WARNING] LivePilot is moving quickly. Pin a version for repeatable studio or live-performance setups, and check the changelog before updating.

Start Here

The setup wizard installs the Ableton Remote Script, creates the Python environment, copies the Max for Live Analyzer, and checks the connection:

npx livepilot --setup

Using Claude Desktop? Download the latest livepilot-<version>.mcpb from Releases and double-click it.

See Install for client-specific setup and manual options.

What's New in v1.30.0

LivePilot now spends far less context describing itself and gives clearer answers about what it actually knows.

• A focused first contact. Normal sessions advertise 28 useful entry points instead of sending all 474 schemas up front. The rest remain searchable and directly callable.
• Options that mean something. Decorative Composer, Atlas, and routing parameters are gone; sample roles and material filters now change the result; unsupported abstract events fail with concrete guidance instead of disappearing silently.
• Evidence with a label. Mix and evaluation reports separate measured audio, setup-derived heuristics, and artistic judgment. “Less bright” and other reduction goals now score in the right direction.
• Depth when it earns its keep. Quick creative requests take a quick path. Three-way exploration, broad memory reads, and full critic passes are reserved for real ambiguity.
• More resilient sessions. Startup no longer waits on optional services, ambiguous network failures do not replay destructive edits, and project memory follows the Live set rather than ordinary edits inside it.

Previous release v1.29.0 introduced learned perceptual taste, honest confidence gates, optional CLAP distance, and named Arrangement locators.

Full details in the CHANGELOG.

What LivePilot Does

LivePilot works at two levels: exact control when you know what you want, and informed help when you do not.

Under the hood: a 5,264-device atlas, 683 mapped drum kits, 29 sample-processing techniques, 44 semantic moves, real-time and offline listening, and 12 planning and evaluation systems. The sections below show how each part works.

Two Ways to Talk to LivePilot

Start with the language that fits the moment. Both routes reach the same tool surface.

Route A — Artist / aesthetic shorthand

"Sound like J Dilla."   "Make this feel more like Burial."   "BoC-style pads."

Use a producer or genre as shorthand for rhythm, density, space, texture, and device choices. LivePilot translates the reference into techniques rather than pretending to clone someone's identity.

Route B — Direct musical intent

"Push the snare 4 ms early, keep the kick on-grid, add ±2 ms timing variation to the hats, and cut 3 dB around 380 Hz on the snare."

When the detail matters, name it: notes, milliseconds, dB, frequency, modulation depth, envelope shape, send level, automation curve, scale degree, or voice leading.

Mixing the routes

Most sessions use both. Start broad, listen, then get specific where the track needs it.

Architecture

┌──────────────────────────────────────────────────────────────────────┐│                                                                      ││  KNOWLEDGE               PERCEPTION              MEMORY              ││  ──────────────          ──────────────          ──────────────       ││                                                                      ││  Device Atlas            9-band FFT              recall by mood,     ││  5264 devices            RMS / peak              genre, texture      ││  120 enriched             pitch tracking          29 techniques       ││  683 drum kits           key detection           replay into session ││                                                                      ││  Sample Engine           Corpus Intelligence     Taste Graph          ││  Splice (local SQLite)   EmotionalRecipe         move preferences    ││  Browser search          GenreChain              device affinities   ││  Filesystem scan         PhysicalModelRecipe     novelty tolerance   ││  6 fitness critics       AutomationGesture                           ││                                                                      ││  ┌──────────────┐  ┌──────────────┐  ┌──────────────┐               ││  │  Device      │  │  M4L         │  │  Technique   │               ││  │  Atlas       │──│  Analyzer    │──│  Memory      │               ││  └──────┬───────┘  └──────┬───────┘  └──────┬───────┘               ││         │                 │                  │                        ││  ┌──────┴───────┐  ┌──────┴───────┐  ┌──────┴───────┐               ││  │  Sample      │  │  Corpus      │  │  Composer    │               ││  │  Engine      │  │  Intelligence│  │  Engine      │               ││  └──────┬───────┘  └──────┬───────┘  └──────┬───────┘               ││         └─────────────────┼──────────────────┘                       ││                           ▼                                          ││                  ┌─────────────────┐                                  ││                  │   474 MCP Tools  │                                  ││                  │   57 domains     │                                  ││                  └────────┬────────┘                                  ││                           │                                          ││           Remote Script ──┤── TCP 9878                                ││           M4L Bridge ─────┤── UDP 9880 / OSC 9881                    ││           Splice (local) ─┤── SQLite (downloaded samples)             ││                           │                                          ││                  ┌────────────────┐                                   ││                  │  Ableton Live  │                                   ││                  │      12        │                                   ││                  └────────────────┘                                   │└──────────────────────────────────────────────────────────────────────┘

How the pieces connect

Remote Script (remote_script/LivePilot/) — A Python ControlSurface that runs inside Ableton's process. Listens on TCP 9878. All Live Object Model calls execute on Ableton's main thread via schedule_message. Detects Ableton version at startup and enables four capability tiers: Core (12.0+), Enhanced Arrangement (12.1.10+), Full Intelligence (12.3+), Collaborative (12.4+).

MCP Server (mcp_server/) — Python FastMCP server. Validates inputs, routes commands to the Remote Script over TCP, manages the M4L bridge, and runs the atlas, sample engine, composer, planning, and evaluation systems. This is what your AI client connects to.

M4L Bridge (m4l_device/) — Optional Max for Live Audio Effect on the master track. Provides deep LOM access through Max's LiveAPI that the ControlSurface API can't reach. UDP 9880 (M4L to server) carries spectral data and LiveAPI responses. OSC 9881 (server to M4L) sends commands. The 38 spectral/analyzer tools strictly require the bridge; device and sample tools that call the bridge also have graceful fallbacks, so core functionality works without it. Backed by 32 bridge commands for hidden parameters, Simpler internals, warp markers, display values, and Simpler warp / Compressor sidechain writes that live on child objects Python can't reach.

Device Atlas (mcp_server/atlas/) — In-memory indexed JSON database. 5264 devices with browser URIs (bundled baseline), 120 enriched with YAML sonic profiles (mood, genre, texture, recommended chains). 7 indexes: by_id, by_name, by_uri, by_category, by_tag, by_genre, by_pack. Reverse-index device_techniques_index.json powers atlas_techniques_for_device (146 cross-references across 58 devices). Device and preset choices resolve against the atlas before loading, which reduces guessed names and dead ends. v1.22.0+: run scan_full_library after install to index your packs, User Library, and plugins into ~/.livepilot/atlas/device_atlas.json — your personal atlas overrides the baseline and survives npm updates.

Sample Engine (mcp_server/sample_engine/) — Searches three sources simultaneously: BrowserSource (Ableton's library), SpliceSource (local Splice catalog via SQLite), FilesystemSource (user directories). Every result passes through a 6-critic fitness battery (key, tempo, spectral, genre, mood, technical). 29 processing techniques (Surgeon precision vs. Alchemist experimentation). Builds complete sample processing plans with warp, slice, and effect recommendations.

Splice Client (mcp_server/splice_client/) — Searches Splice's catalog through two layers: the local SQLite database (sounds.db, already-downloaded samples) and the live gRPC API (full catalog, including samples you haven't downloaded yet). The gRPC client auto-detects Splice's dynamic port via port.conf, handles self-signed TLS, and enforces a 5-credit safety floor before any download. Per-call timeouts (5–10s) prevent a hung Splice process from stalling the MCP event loop. Graceful fallback to SQL-only if grpcio isn't installed. No API key needed — authentication comes from the running Splice desktop app.

Composer (mcp_server/composer/) — Prompt-to-plan pipeline. Parses natural language ("dark minimal techno 128bpm with industrial textures") into a CompositionIntent (genre, mood, tempo, key). Plans layers using role templates (kick, bass, percussion, texture, lead, pad, fx). Compiles to a step-by-step plan of tool calls that the agent executes. Does not execute autonomously — returns the plan. 4 genre defaults (house, techno, trap, ambient) — genres outside this set fall back to a neutral layer plan.

Corpus (mcp_server/corpus/) — Parsed device-knowledge markdown converted to queryable Python structures: EmotionalRecipe, GenreChain, PhysicalModelRecipe, AutomationGesture. Feeds Wonder Mode, Sound Design critics, and the Composer with structured production references at runtime.

Execution Router (mcp_server/runtime/execution_router.py) — Classifies each step in a multi-step plan as remote_command (TCP to Ableton), bridge_command (OSC to M4L), or mcp_tool (internal), then dispatches it through the correct channel.

How LivePilot Makes Decisions

Tools make the edit. These 12 systems help decide what to try, what to protect, what to compare, and what to remember.

SongBrain — What the Song Is

Builds a real-time model of the session: identity core (what defines this track), sacred elements (what must not be casually damaged), section purposes (what each part is doing emotionally), energy arc (where the song is heading). Detects identity drift when edits pull the track away from what made it work.

Taste Graph — What You Like

Learns your production preferences across sessions. Tracks which move families you keep vs. undo, which devices you gravitate toward, how experimental you want suggestions (novelty band), and which dimensions you avoid. Every accept/reject updates the graph. Two producers using the same tools get different recommendations.

Semantic Moves — Musical Actions, Not Parameters

44 high-level intents across 7 families (mix, arrangement, transition, sound_design, performance, device_creation, sample) — "add contrast," "tighten the low end," "make kick and bass lock," "sample vocal ghost," "destroy then rebuild." Each move compiles into a concrete tool sequence with risk level, target dimensions, and protection thresholds. Analyzer-gated moves (tighten_low_end, make_kick_bass_lock) mark their spectrum pre-reads as optional so the plan continues even when the analyzer isn't available. The plan shows its tradeoffs before anything changes.

Wonder Mode — Stuck-Rescue Workflow

When a session is stuck — repeated undos, overpolished loops, no structural progress — Wonder Mode activates:

1. Diagnose — classify the stuckness (loop trap? missing contrast? identity unclear?)
2. Generate — find semantic moves that address the diagnosis, enforcing real distinctness
3. Preview — apply each variant, capture, undo. Hear before committing
4. Commit or Reject — choice recorded into taste and session continuity

Creative Engines

Hook Hunter

Identifies the most salient musical idea — ranks candidates by recurrence across scenes, motif salience, and section placement (payoff-section boost). Tracks whether hooks are developed, neglected, or undermined, and flags when a transition fails to deliver expected payoff. Rhythm-side ranking is currently heuristic (drum-track detection + clip reuse); true onset-based rhythmic features are on the roadmap.

Session Continuity

Maintains creative threads ("the chorus needs more lift") and turn resolutions across the session. When you return to a project: "Last time, you kept the filter sweep for the bridge. The chorus lift thread is still open."

Evaluation Loop

Every engine follows: measure before → act → measure after → compare. If a change made things worse (more masking, lost headroom, identity drift), the system flags it before you move on.

Tools

LivePilot has 474 tools across 57 domains, but it no longer sends that entire schema to the AI on every connection. The default producer profile exposes a focused 26-tool production loop plus search_tools and call_tool; every other tool remains searchable and directly callable by name. This keeps the initial catalog under 40 KB while preserving the full system.

Use LIVEPILOT_TOOL_PROFILE=composition, mixing, or sampling to pin more domain tools. Set LIVEPILOT_TOOL_PROFILE=full for legacy clients or catalog diagnostics. Highlights below — full catalog here.

Core Ableton Control — highlights

M4L Bridge — 38 analyzer tools [optional], 32 bridge commands

The M4L Analyzer sits on the master track. UDP 9880 carries spectral data to the server. OSC 9881 sends commands back. The ensure_analyzer_on_master pre-flight (v1.20.3) loads the analyzer idempotently when an audio-dependent decision needs it.

[!TIP] Most tools work without the analyzer — it adds 38 spectral/analyzer tools (frequency, loudness, perception, Simpler, warp) and closes the feedback loop.

SPECTRAL ─────── 9-band frequency decomposition (sub_low → air)                 sub_low (20-60 Hz) split off so kick fundamentals don't hide inside sub                 true RMS / peak metering                 Krumhansl-Schmuckler key detection
DEEP LOM ─────── hidden parameters beyond ControlSurface API                 automation state per parameter                 recursive device tree (6 levels into nested racks)                 human-readable display values as shown in Live's UI
SIMPLER ──────── replace / load samples                 get slice points, crop, reverse                 warp to N beats, get audio file paths
WARP ─────────── get / add / move / remove markers                 tempo manipulation at the sample level

Device Atlas — 13 tools

The atlas is an in-memory indexed database of Ableton's entire device library.

5264 devices total  120 enriched with sonic intelligence (mood, genre, texture, chains)   47 with aesthetic-tagged signature_techniques  683 drum kits mapped with note assignments    7 indexes: by_id, by_name, by_uri, by_category, by_tag, by_genre, by_pack  146 technique cross-references across 58 devices (reverse-index)

atlas_search                   Search devices by name, category, or tagatlas_device_info              Full enriched profile for a single deviceatlas_suggest                  Suggest devices for a musical intent (e.g., "warm pad")atlas_chain_suggest            Build a device chain from a genre, artist, or purposeatlas_compare                  Compare two devices side-by-sideatlas_describe_chain           Free-text describe-a-chain ("granular pad like Tim Hecker")atlas_techniques_for_device    Reverse-lookup: what techniques reference this device?atlas_pack_info                Inspect a single Ableton pack — devices + enrichment coveragescan_full_library              Scan what's actually installed on this machinereload_atlas                   Hot-reload the atlas after adding enrichmentsextension_atlas_search         [v1.23.0+] Search user-local atlas overlaysextension_atlas_get            [v1.23.0+] Fetch a single overlay entry by namespaceextension_atlas_list           [v1.23.0+] Enumerate overlay namespaces + entity_type counts
# Pack-Atlas Phase C-F (v1.23.4+) — corpus-driven orchestrationatlas_macro_fingerprint        [v1.23.4+] "More like this" — find similar presets across 3,813 sidecars by macro fingerprintatlas_transplant               [v1.23.4+] Adapt a demo / preset / workflow to new BPM, scale, or aesthetic — PRESERVE / SCALE / REMAP / REPLACE decisionsatlas_demo_story               [v1.23.4+] Track-by-track narrative + production sequence inference for any of 104 factory demo .alsatlas_extract_chain            [v1.23.4+] Surgically rebuild a demo track's device chain as an executable plan (load_browser_item + insert_device + set_device_parameter)atlas_pack_aware_compose       [v1.23.4+] Bootstrap a project with pack-coherent track selection from an aesthetic brief; supports `pack_diversity="eclectic"` modeatlas_cross_pack_chain         [v1.23.4+] Execute any of 15 cross-pack workflow recipes step-by-step with aesthetic overrides (target_scale / target_bpm / transpose_semitones)

v1.23.0 — User-local extensions: Drop YAML files at ~/.livepilot/atlas-overlays/<namespace>/ to extend the atlas with custom hardware libraries, signature chains, or technique recipes — survives npm updates. See docs/EXTENSION_API.md.

v1.23.4 — Pack-Atlas Phases C/D/E/F: Six new corpus-driven orchestration tools turn the 3,917 parsed pack sidecars + 104 demo .als parses into actionable artifacts — find similar presets, transplant aesthetics across BPM/scale/genre, narrate a demo, extract a track's chain as a runnable plan, bootstrap pack-coherent compositions, run any of 15 cross-pack workflow recipes. All execution is dry-run by default — returns plans, doesn't auto-mutate the session.

User Corpus — 14 tools [v1.23.4+]

Why this exists. The factory atlas covers what Ableton ships. Most studios also have third-party plugins, Max for Live devices, custom racks, presets, and sample packs. The corpus builder indexes that local library so recommendations can use tools you actually own.

The corpus builder turns what is installed on your machine into searchable production context:

Phase 1 — DETECT      Walk plugin folders + run `auval -a` for AUv3 / Mac Catalyst                       coverage. Captures format (VST3/AU/AAX/CLAP/LV2),                       vendor, version, bundle ID. ~40-200 plugins typical.
Phase 2 — CANONICALIZE Dedupe by vendor+name, prefer VST3 over AU, strip vendor                       suffix variants ("Valhalla DSP, LLC" = "Valhalladsp" =                       "Valhalla DSP"). Cluster by vendor for batch research.
Phase 3 — RESEARCH    Discover local manual files (PDFs, READMEs) per plugin.                       Prepare focused plugin and technique research tasks.
Phase 4 — SYNTHESIZE  Build a per-plugin identity.yaml                       with sonic_fingerprint / reach_for / avoid / key_techniques /                       parameter_glossary / comparable_plugins / genre_affinity /                       producer_anchors. Keep one primary format tag (no                       dual-indexing across formats).

The result lives at ~/.livepilot/atlas-overlays/user/plugins/<plugin_id>/identity.yaml and is available to atlas_search, atlas_chain_suggest, atlas_macro_fingerprint, and atlas_describe_chain alongside the factory atlas. Every result names its source (factory_atlas or user_overlay:user), so you can see whether a recommendation comes from Ableton stock or your own gear.

corpus_setup_wizard            One-shot orchestration — runs the full pipelinecorpus_init                    Initialize ~/.livepilot/corpus/ + manifest.yamlcorpus_status                  Inspect manifest, sources, scan historycorpus_list_scanners           Enumerate registered scanner typescorpus_add_source              Register a new scan source (project / racks / Max / samples)corpus_remove_source           Remove a scan source from manifestcorpus_scan                    Run scanners on configured sourcescorpus_detect_plugins          Phase 1 — VST3 / AU / AUv3 / VST2 / AAX / LV2 detectioncorpus_canonicalize_plugins    Phase 2 — dedupe + VST3-preferred + suffix stripcorpus_cluster_plugins         Phase 2.5 — group by vendor for efficient research dispatchcorpus_trim_plugin_identity    Slim a yaml to the overlay-required minimumcorpus_discover_manuals        Phase 3 — locate local PDFs / READMEs per plugincorpus_research_targets        Phase 3 — prepare research tasks for the agentcorpus_emit_synthesis_briefs   Phase 4 — prepare identity briefs per plugin

Why this matters. A static index goes stale when your library changes. Re-scan after adding a plugin or rack and LivePilot can consider it alongside Ableton's factory devices.

Quick start:

# In your MCP client (Claude Code / Desktop / Cursor):corpus_setup_wizard                              # one-shot orchestration# OR fine-grained control:corpus_detect_plugins use_auval=true             # finds AUv3 / Mac Catalyst pluginscorpus_canonicalize_plugins                      # VST3 preference + vendor dedupcorpus_cluster_plugins                           # vendor-grouped clusterscorpus_research_targets                          # → agent researches the pluginscorpus_emit_synthesis_briefs                     # → agent writes identity profiles

See docs/USER_CORPUS_GUIDE.md for full walk-through, docs/PLUGIN_KNOWLEDGE_ENGINE.md for engine internals, and livepilot/skills/livepilot-corpus-builder/SKILL.md for the agent skill that drives the pipeline.

Sample Engine — 23 tools

Search Ableton, local folders, and Splice together, then rank results against the musical role instead of returning a pile of filenames.

SOURCES ─────────── BrowserSource  (Ableton's built-in library)                    SpliceSource   (local Splice catalog via SQLite)                    FilesystemSource (user-specified directories)                    Splice LIVE    (gRPC + GraphQL for the full catalog)
CRITICS ─────────── key fitness · tempo fitness · spectral match                    genre alignment · mood alignment · technical quality
TECHNIQUES ─────── 29 processing recipes:                    Surgeon (precise, transparent) vs.                    Alchemist (experimental, transformative)
PLAN-AWARE ─────── Ableton Live plan   100 samples/day (no credit drain)                    Sounds+/Creator     CREDIT_HARD_FLOOR=5 safety gate                    Free samples        bypass both gates

Sample analysis & planning  analyze_sample            Build complete SampleProfile (material, key, BPM, spectral)  search_samples            Multi-source search with critic scoring  evaluate_sample_fit       Score a candidate sample against session context  suggest_sample_technique  Recommend processing technique for a sample  plan_sample_workflow      Full processing pipeline: warp + slice + effects  plan_slice_workflow       Slice-specific workflow for breaks / drum loops  get_sample_opportunities  Surface sample-friendly spots in the session
Splice LIVE (catalog, collections, presets)  get_splice_credits        Plan + remaining credits + daily quota state  splice_catalog_hunt       Query the full Splice catalog (gRPC)  splice_download_sample    Plan-aware download (credit floor + quota check)  splice_preview_sample     Zero-cost audition via PreviewURL  splice_describe_sound     Natural-language search via Splice GraphQL  splice_generate_variation Find catalog samples similar to a given UUID  splice_list_collections   Enumerate user's Likes / bass / keys folders  splice_search_in_collection / add_to_collection / remove_from_collection / create_collection  splice_list_presets       Purchased instrument presets  splice_preset_info · splice_download_preset  splice_pack_info          Per-pack metadata  splice_http_diagnose      Debug the Splice HTTPS bridge

Splice Integration

LivePilot reads Splice's local SQLite database to search your downloaded samples with full metadata. No API key needed — it reads the database file directly.

What it does:

• Searches your downloaded Splice samples with key, BPM, genre, and tag metadata
• Integrates as a third source alongside Ableton's browser and filesystem scanning
• Works without a Splice subscription — any previously downloaded samples are searchable

How it works: The Sample Engine's SpliceSource reads ~/Library/Application Support/com.splice.Splice/users/default/*/sounds.db — Splice's local SQLite catalog of downloaded samples. Read-only, no network calls.

Requirements: Splice desktop app running (the MCP server talks to it over gRPC at a dynamic port advertised via port.conf, with self-signed TLS). For fully offline search, previously-downloaded samples are always searchable via the local SQLite fallback even if the Splice app isn't running.

Composer — three modes (v1.25.0)

Prompt-to-plan composition workflow. Three modes share the same safety checks: reconnect the bridge, load the analyzer when needed, set monitoring correctly on new tracks, and return to Arrangement View after the build. The work stays visible as a sequence of tool calls.

"dark minimal techno 128bpm with industrial textures and ghostly vocals"    │    ▼┌─────────────────┐│  Prompt Parser   │ → CompositionIntent (genre, mood, tempo, key)└────────┬────────┘         ▼┌─────────────────┐│  Layer Planner   │ → role templates (kick, bass, perc, texture, lead, pad, fx)└────────┬────────┘         ▼┌─────────────────┐│  Plan Compiler   │ → executable tool sequences└────────┬────────┘         ▼┌─────────────────┐│ Execution Router │ → dispatches: create tracks, search samples, load devices,│                  │   program notes, set volumes, build arrangement└─────────────────┘

fast mode — compose_fast_apply

Quick loop sketch. Single scene in session view. Intended for roughing out ideas quickly.

• Hunt order: curated .adg chains from the browser first, atlas devices second, bare instruments only as last resort
• Drum-role pitch repair included (Simpler default root vs. MIDI 36 offset)
• 4 genre defaults: house, techno, trap, ambient (unknown genres fall back to a neutral layer plan)
• Invoke with: "Make me a [genre] loop at [tempo] BPM"

full mode — compose_full_apply

Full track with song form: intro, verse, hook, breakdown, outro. Uses a two-phase LLM-creative brief flow — the LLM authors the form (sections, track list, per-section variants); the framework supplies the vocabulary (device hunt order, MIDI generation rules, arrangement conventions).

• Per-section MIDI variants prevent repeated tiles across the arrangement
• Native arrangement clips via create_native_arrangement_clip (one clip per section, looped to fill section length)
• Zombie-track cleanup in postflight (removes tracks with no clips and no instrument device)
• Drum-role pitch repair ported from fast mode
• Atlas anchors: role-level device knowledge is supplied through KnowledgePack.atlas_anchors, which consults the indexed atlas rather than filename matching. The older atlas_candidates_per_role field is a deprecated legacy stub, kept empty for back-compat.
• Invoke with: "Write a full [genre] track at [tempo] BPM" or "Build a full arrangement"

develop mode — develop_apply

Extends an existing 8-bar loop without disturbing the seed material.

• Introspects the existing session (classifies tracks by name and content)
• Pulls artist and stylistic references from the user prompt
• Writes per-track variants and new supporting layers alongside the seed
• Invoke with: "Develop this loop" or "Extend what's here into a longer idea"

KnowledgePack scaffolding (v1.25.0)

All three modes share a KnowledgePack that provides structured creative context at runtime:

• event_lexicon — 42 structural events across 7 categories (drum density, harmonic, texture, vocal, rhythm feel, tension, fx gesture)
• genre_context — parses the 15-genre genre-vocabularies.md at load time
• artist_context — parses the ~25-producer artist-vocabularies.md at load time
• atlas_anchors — indexed-atlas device anchors per role (replaced the legacy atlas_candidates_per_role stub)

Core composer tools

• compose — plan a multi-layer composition from text prompt (entry point, mode-agnostic)
• compose_fast_apply — execute fast mode directly
• compose_full_apply — execute full mode directly
• develop_apply — execute develop mode directly
• augment_with_samples — plan sample-based layers for an existing session
• get_composition_plan — dry-run preview (see the plan without credit checks)

Device Forge — 3 tools

Generate M4L audio effect devices from gen~ templates and install them into Ableton's browser.

forge_device           Generate a device from a gen~ templateforge_list_templates   Browse available gen~ templatesforge_install          Install generated device to browser

Planning, Evaluation, and Learning — 79 tools

These tools read the session, diagnose problems, plan changes, compare results, and carry useful context into the next decision.

View all 474 tools →

Install

Claude Desktop: one-click install

Download the latest livepilot-<version>.mcpb from the Releases page and double-click it. Claude Desktop installs everything automatically. Then:

1. Open Ableton Live 12
2. Preferences → Link, Tempo & MIDI → Control Surface → LivePilot
3. Start chatting

[!TIP] The Desktop Extension auto-installs the Remote Script and M4L Analyzer on first launch.

Terminal: one-command setup

npx livepilot --setup

Runs the full setup wizard: checks Python, installs the Remote Script, creates the Python environment, copies the M4L Analyzer, and tests the Ableton connection.

Manual: Step by Step

npx livepilot --install

# MCP server only:claude mcp add LivePilot -- npx livepilot
# Or the full plugin (MCP server + skills + slash commands):claude plugin marketplace add github:dreamrec/LivePilotclaude plugin install livepilot@dreamrec-LivePilot

npx livepilot --install-codex-plugin

{  "mcpServers": {    "LivePilot": { "command": "npx", "args": ["livepilot"] }  }}

npm install -g livepilotlivepilot --install

{  "mcpServers": {    "LivePilot": { "command": "livepilot" }  }}

{  "mcpServers": {    "LivePilot": { "command": "npx", "args": ["livepilot"] }  }}

{  "servers": {    "LivePilot": { "command": "npx", "args": ["livepilot"] }  }}

Verify

npx livepilot --status

Plugin

Codex App

npx livepilot --install-codex-plugin

Claude Code

claude plugin marketplace add github:dreamrec/LivePilotclaude plugin install livepilot@dreamrec-LivePilot

Producer Agent — handles longer jobs in visible stages: reads the session, checks what you kept, searches the library, proposes a plan, applies edits, and listens back. You stay in charge of what remains in the set.

Core Skill — keeps the work disciplined: search before loading, measure before and after, preserve undo, and verify every change.

CLI

npx livepilot              # Start MCP server (stdio)npx livepilot --setup      # Full setup wizardnpx livepilot --install    # Install Remote Scriptnpx livepilot --uninstall  # Remove Remote Scriptnpx livepilot --install-codex-plugin   # Install bundled Codex pluginnpx livepilot --uninstall-codex-plugin # Remove bundled Codex pluginnpx livepilot --status     # Check Ableton connectionnpx livepilot --doctor     # Full diagnostic checknpx livepilot --version    # Show version

Compatibility

Version tiers:

• Core (12.0+): All session tools, mixing, devices, MIDI, theory, generative, memory
• Enhanced Arrangement (12.1.10+): Native arrangement clips, arrangement automation
• Full Intelligence (12.3+): insert_device_native, complete device insertion pipeline
• Collaborative (12.4+): replace_sample_native and newer sample-editing routes that bypass the M4L fallback when Live exposes a native LOM path

Development

git clone https://github.com/dreamrec/LivePilot.gitcd LivePilotpython3 -m venv .venv && .venv/bin/pip install -r requirements.txt# Test runner is not in requirements.txt (runtime-only deps) — install it explicitly:.venv/bin/pip install pytest pytest-asyncio.venv/bin/pytest tests/ -v

See CONTRIBUTING.md for architecture details, code guidelines, and how to add tools.

Documentation

Community

• Discussions — questions, ideas, show & tell
• Bug reports
• Feature requests
• Contributing guide
• Security policy

Support

LivePilot is source-available under the Business Source License 1.1. If it earns a place in your sessions, you can support its continued development:

Sponsor on GitHub

Sponsorship funds deeper Ableton coverage, cross-platform testing, and maintained technique libraries. Sponsors also get early builds and direct support.

BSL-1.1 — Pilot Studio

Sister projects: TDPilot (TouchDesigner) · ComfyPilot (ComfyUI)