Open the books

RAW FILE: ROSTER.md (Kid Katapult)

Source game/ROSTER.md in the jam repo. Last git commit of this file: 2026-11-12. About 707 words. Scrubbed only for private details and one line about another entrant. Mistakes left in on purpose.

Crew and equipment: who does what during the jam

Thu Nov 12, about 00:45 ET. Source of truth for machines and tools: studio-pipeline/registry/TOOLS.md (Machines, Models) and docs/MACHINES-FOR-DON.md. Don's framing: this jam is the origin story of the autonomous studio. Every method that works becomes a reusable studio job, not a one-off.

Rule one: nothing idles

The queue sends every job to tower 1 unless its spec says otherwise (run_on defaults to ["tower1"] in tools/queue/policy.py). So the laptop's 4090 and tower 2's 48 threads sat idle overnight. From now on every job spec names its machine on purpose: run_on: ["laptop"], ["tower1"], or machine: "cpu" with tower2_ok: true.

The three machines

MachineJam roleRunsFree models and tools it holds
Laptop, RTX 4090 16 GB, WindowsThe stage: the only Unreal editor that builds, and the only compiler, so all packaging (code project, MetaHuman, LiveLink and ChaosClothAsset enabled)UE 5.9 editor over MCP, packaging, Movie Render Queue for the film, ComfyUI when the editor is closedComfyUI (FLUX.2 klein, FLUX.1 schnell, TRELLIS.2, Pixal3D, Wan 2.2), Blender Cycles, Kimodo (no text encoder cached here yet), voices (Chatterbox, Kokoro, Dia, Qwen3-TTS, Maya1, VoxCPM2), Ollama (gpt-oss 20b, qwen3 14b, qwen3-vl 8b), OBS, Android SDK and JDKs, butler
Tower 1, RTX A5000 24 GB, UbuntuThe factory and the critics: all generation overnight, and free judgingQueue jobs: images, 3D props, textures, music, voices, motion, video previzComfyUI (same models plus Wan 2.2 at 720p), ACE-Step 1.5, Kimodo SOMA (cleared for commercial use; the SMPL-X variant never), Chatterbox, Kokoro, Dia, Maya1, VoxCPM2, faster-whisper, Demucs, RIFE 4.9, Marigold, PBRify, Blender, Ollama (qwen3-vl 32b, qwen3.5 27b, gemma4 31b, qwen3-coder 30b), critics (speaker and accent ECAPA, audiobox-aesthetics, CLAP)
Tower 2, Threadripper 48 threads, W6600 (no CUDA), WindowsSecond unit and QA: the test editor, CPU work, bot playtestsMetaHuman builds by script (signed in, MCP on port 8000), headless UE runs and frame captures, Blender CPU renders, bot playtests, CI, packaged-build smoke testsUE 5.9 with MetaHuman content, Blender, Godot, OBS, VMware

Free brains (no Claude tokens)

Claude, by tier (ORG.md)

Pipeline for one take

  1. Story beat in STORY.md, then a shooting script (prep/scripts/director/ format) with cues and every fail branch.
  2. Motion: Kimodo candidates on tower 1, the motion gate, retarget to the MetaHuman skeleton (twist the upper arm and thigh), joint-limit check.
  3. Set: props (TRELLIS.2 via ComfyUI), textures, Megascans kits we already hold for dressing, lights.
  4. Voice and sound: director and crew lines in Chatterbox or Dia, the takes check, then sound effects and score.
  5. Unreal on the laptop: Sequencer take, cue gate, fail branches, edit bay. Second-unit captures on tower 2.
  6. Critics: qwen3-vl first pass, then a fresh Claude reviewer against STANDARDS.md, then the board for Don.

Running now