Turn natural language and reference images into print-ready 3D files (STL/3MF/GLB/STEP) through an interactive design session. A local-first, manifold-by-construction CAD engine the agent authors — every model ships forever-editable parametric SOURCE, is validated against a 4-dimension print-readiness check (watertight/manifold/single-body, optional real headless slice for D2, wall/overhang/bed geometry, workflow) with an auditable Print-Readiness Certificate, and is judged by a vision-grounded, kernel-metrics-fused fidelity loop with a disconnected-part gate. Includes a DFAM/CSG domain knowledge base, an artistic style system, a packaged reference library of subject proportions, a JSON design-plan source-of-truth, multi-part assemblies with interference checks, AMS multicolor, printer profiles, git-tracked history, and a live React + three.js preview UI with a parametric customizer.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Run an interactive "Grill-me" design session that pins down an underspecified 3D model through focused questions, then produces a validated design plan (design.json) — the project's base design — and hands off to generation + a vision-grounded fidelity loop. Use when the user says "grill me", "design session", "help me design", "let's design a <thing>", "spec out my model", "interview me about my model", or gives a vague modeling request that needs nailing down before building. The session grounds every question in the packaged reference brief and artistic style system, asks only what is genuinely ambiguous, proposes sensible defaults, and emits a complete design plan you regenerate from on every tweak.
Run an interactive 3D design session — turn a natural-language description (and optional reference images) into print-ready 3D files (STL + 3MF + GLB) in output/, validated for 3D printing and visually verified to match intent. Use whenever the user wants to model, design, generate, mock up, tweak, modify, or 3D-print an object — a bracket, enclosure, stand, holder, knob, gear, fixture, sign, figurine, vase, toy, or any physical part — for Bambu Studio, OrcaSlicer, PrusaSlicer, or MakerWorld. Also use to load and modify an existing STL/3MF/GLB. Triggers on "model a…", "design a…", "make me a printable…", "generate an STL of…", "tweak the…", "I want to 3D print a…".
Admin access level
Server config contains admin-level keywords
A Claude Code plugin + agent harness that turns a natural-language description (and optional reference images) into print-ready 3D files (STL · 3MF · GLB) you can drop straight into Bambu Studio, OrcaSlicer, PrusaSlicer, or MakerWorld — validated against the 2026 AI 3D Print-Readiness Benchmark, with a React + three.js preview UI.
The agent does the modeling. The primary engine is a local, manifold-by- construction CSG kernel that the agent writes geometry against — deterministic, free, needs no GPU or API key, and produces watertight solids by construction (~100% slicer pass). An optional generative backend (Meshy / local models) handles genuinely organic shapes, always followed by validate → repair.

3D Studio competes with generative-mesh tools (Meshy/Tripo) not on organic mesh
aesthetics — their saturated home turf — but on the properties a diffusion-mesh cloud
tool is architecturally barred from matching. See docs/V3-COMPETE-WITH-MESHY.md.
studio3d slice / validate --slice drives a
detected OrcaSlicer/Bambu/PrusaSlicer/Cura headless to produce real G-code with real
print time + filament grams — verified end-to-end against Bambu Studio 2.7.1 (e.g.
"25m 43s, 3.5 g"). With no slicer it falls back to an explicitly labeled proxy
(d2_method), so "print-ready" is never silently self-certified.studio3d slicer status detects the OS/arch and any
installed slicer (native / AppImage / .app / flatpak); studio3d slicer install gives the
exact per-OS recipe (OrcaSlicer AppImage on Linux, brew --cask on macOS, winget on
Windows) and performs it with --yes.model.py + params.json.
Change one knob (studio3d tweak --set wall=3) and regenerate deterministically. A
Meshy mesh has no knobs to turn.certificate.json — prompt → script/file hashes →
D1–D4 → slice result → human-approval slot — an auditable provenance chain.design-critic runs on a stronger model and
reads genus / component-count / wall-p05 / overhang alongside the renders (catches
defects invisible in a 4-view image), with an anti-stagnation escalate verdict.paint() each part and combine with
multicolor_union(...). The exporter writes the Bambu/Orca native format — separate
objects with per-object extruder (filament) assignment in model_settings.config plus
an N-filament project_settings.config built from Bambu's own template — not core-3MF
colorgroups (which Bambu ignored: "no filament colors found"). The per-object filament
routing is verified to survive a Bambu Studio round-trip (objects → deduped slots
1,2,3…). Open in Bambu/Orca with a printer selected to map parts to AMS slots; identical
part colors dedupe to one slot. (Headless GUI color display isn't scriptable here, so
that last visual step is confirmed by opening the file, not in CI.)studio3d step, or --formats …,step) — a dependency-free
AP214 MANIFOLD_SOLID_BREP (no OCP kernel needed on CPython 3.14). The output is
structurally verified (sewn closed shell, consistent orientation, coplanar faces);
acceptance by a specific CAD kernel is best-effort and not yet round-trip-confirmed in
Fusion/SolidWorks here.mates, a single clearance_mm knob,
and an automated interference() collision check.studio3d kb) grounds authoring in documented rules.print_ready fails when a model that should be one solid
comes out in detached/levitating pieces (n_components > expected) — a watertight-per-
piece model is not print-ready if it's in fragments.studio3d muse). This is NOT the MUSE
benchmark and its number is not comparable to it: it runs bundled reference scripts
(the answer key) through fabricate→validate and reports how reliably the deterministic
kernel + validator produce print-passing solids. It measures pipeline reliability, not
text→CAD generation quality (the hard part — turning a prompt into geometry — is done by
the agent, and a blind held-out eval is the honest measure of that).Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub kryptobaseddev/3d-ai-studio --plugin 3d-studioHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows