explainx.ai350K+ learn from us
TrendingAI News TodayExplainx for Business
Pricing
explainx.ai

Upskill in AI — 16 free pathways, live workshops & bootcamps, and 50+ courses from practitioners. Plus the skills, tools, and MCP servers to practice on.

follow us

follow on google

Add explainx.ai as a preferred source

corporate training

support@explainx.ai

get started

Find your pathTake Free Evaluation

community

Join the community

learn

mind: share how you thinkpathways — start freeworkshopsbootcampscoursescompare Explainxcertificationsmock testsexplainx universitycorporate traininglearn skills & mcp

discover

skillsmcp serversexplainx mcpestacktoolsmdx readeragentsllmsdesignsdictionarypeopleagi trackerfelony benchranks

company

aboutvisionmissionteaminstructorsteach on explainxpartnershipscommunityhackathonscareers

content

daily AI newsstate of AI — live resultsblogreleasespromptsgeneratorsresource libraryfor LLMsexplainx.ai kids

solutions

all solutionsdeveloper upskillingmarketing upskillingproduct manager upskillingleadership upskilling

newsletter · weekly

Get AI news, tools, and insights in your inbox.

supportcontactprivacytermsdata rightshow we create contentsubmission guidelines

© 2026 AISOLO Technologies Pvt Ltd

explainx.ai

On this page

  • What problem sand3d solves
  • How a sand3d program is structured
  • Token efficiency: what Sandflow measures
  • Export matrix: where files go
  • Giving sand3d to your coding agent
  • Hugging Face datasets
  • Install constraints builders hit early
  • How sand3d fits explainx.ai's agent stack
  • Verb surface: what the API actually exposes
  • Testing and determinism in CI
  • Who Sandflow is
  • Limits and honesty
  • FAQ alignment with search intent
  • Security and supply-chain notes
  • When not to pick sand3d
  • A practical evaluation plan
  • Related reading
← Back to blog

explainx / blog

sand3d: Python 3D Modeling Built for LLMs, Not Blender Scripts

Open Source, Robotics, Coding Agents, 3D Modeling, Guides

Part of AI Tools and Apps

Sandflow sand3d is a Python library for procedural 3D assemblies LLMs can write in hundreds of tokens. Exports GLB, URDF, USD, IFC; Apache 2.0; five Hugging Face datasets.

Nov 19, 2026·9 min read·Yash Thakker
add explainx.ai
go deep
sand3d: Python 3D Modeling Built for LLMs, Not Blender Scripts

sand3d is a Python library for 3D objects written as short programs LLMs can read and edit, not as thousand-line Blender scripts. Sandflow-ai/sand3d on GitHub had more than 2,150 stars when explainx.ai checked on November 19, 2026, after roughly two weeks of public development since November 3, 2026.

The project sits at the intersection of physical AI datasets, robotics code generation, and agent tool design: if your agent must emit geometry, you need an API that survives context limits.

Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

What problem sand3d solves

Frontier models can describe shapes in natural language, but executable 3D usually collapses into bpy or CadQuery snippets that burn context on coordinates and booleans. Sandflow's pitch is named, deterministic programs: every part, edge, face, and joint has a label; the same source rebuilds the same mesh bit-for-bit.

The README lists four measurable claims:

table · 2 cols
ClaimWhat it means for builders
2–6× fewer tokens per partMedian comparison versus Blender Python, CadQuery, FeatureScript (vendor chart)
~3,600-token API surfacedocs/api.md fits beside system instructions
Named geometryNo hand-computed vertex lists in prompts
Deterministic buildsSame program yields identical meshes for eval replay

Those numbers come from Sandflow's documentation, not independent labs. They are still useful design targets when you pick a 3D tool for agents.

How a sand3d program is structured

sand3d exposes one flat namespace: import sand3d as s3d. Families include profiles (rect, slot, text), solids (extrude, loft, sweep), edits (hole, fillet, shell), joints, and assembly.

Example: bracket in millimetres

The README's starter bracket uses extrude, patterned holes, and fillet:

python
import sand3d as s3d

def bracket(w=80, d=40, t=6, hole_d=6.6, pitch=50):
    plate = s3d.extrude("plate", s3d.rect(w, d, r=4), t)
    s3d.hole(plate, hole_d, on=s3d.grid(2, 1, pitch, 0))
    s3d.fillet(plate, 1, edges="top")
    return plate

s3d.export(bracket(), "bracket.glb")

Millimetres are default. One export call picks format from the extension.

Example: washing machine with joints

Sandflow's flagship demo models a front-loading washer: cabinet, drum, door, drawer, dial, plus four joints (hinge, continuous spin, prismatic slide, continuous dial). The README shows roughly 38 lines for the full assembly—small enough for a single model completion with room for critique loops.

sand3d washing machine assembly with named joints for LLM procedural 3D modelingsand3d washing machine assembly with named joints for LLM procedural 3D modeling Image: Sandflow

Joint semantics map cleanly to simulators:

  • Revolute door hinge with numeric range
  • Continuous drum rotation
  • Prismatic drawer travel on an axis

That is the difference between pretty meshes and things Isaac or MuJoCo can load, a gap teams hit when moving from Cosmos synthetic data to deployable URDF.

Token efficiency: what Sandflow measures

Token count chart comparing sand3d to Blender Python for LLM 3D codeToken count chart comparing sand3d to Blender Python for LLM 3D code Image: Sandflow

The README chart plots median tokens per part across comparable objects. Sandflow argues low-rank-style coordinate math in other APIs forces models to spend tokens on arithmetic instead of structure.

For agent builders, the actionable test is simpler: count tokens for your part catalog under sand3d versus bpy on ten representative brackets, enclosures, or gripper fingers. If you run replica-skill-style app cloning, geometry is often the longest hidden cost.

Export matrix: where files go

s3d.export(model, path) routes by extension:

table · 3 cols
FormatCarriesTypical downstream
GLBMeshes, materials, joint extras at current poseWeb viewers, game engines
URDFLinks, joint limits at rest; OBJ meshes alongsideROS 2, PyBullet, MuJoCo, Isaac
USDA / USDC / USDZOpenUSD scene graphOmniverse, Isaac Sim
IFC4BIM assemblies (current pose; joint metadata omitted)Revit via IFC link, Tekla
OBJ / STLMeshes onlySlicers, generic DCC tools

Sandflow notes Revit .rvt is not writable by third-party libraries; IFC is the interchange path. IFC GlobalIds can shift when geometry edits—do not use them as stable part IDs across exports.

Giving sand3d to your coding agent

Sandflow ships llms.txt pointing at docs/api.md for the full vocabulary. For multi-part objects, docs/guidelines.md lists eight assembly rules: plan first, then parts, then joints.

That mirrors how MCP servers document tool schemas: keep the contract in-repo so Claude Code, Cursor, or Codex can loop on export failures without guessing bpy internals.

Recommended workflow:

  1. Pin Python 3.13 + bpy 5.2 in your devcontainer or VM.
  2. Paste api.md into system context once per session.
  3. Ask the agent for named parts and joint declarations before mesh detail.
  4. Run s3d.export to GLB for visual QA; URDF when sim semantics matter.
  5. Store programs in git—the source of truth—not binary meshes alone.

Hugging Face datasets

Sandflow published five datasets under CC BY 4.0, each rebuilding external corpora as sand3d programs:

  • sand3d-objaverse — everyday objects from Objaverse
  • sand3d-cad — mechanical parts from public CAD
  • sand3d-articraft — articulated objects with declared joints
  • sand3d-simready — NVIDIA SimReady assets
  • sand3d-automate — AutoMate mechanical assemblies

An explorer on Sandflow's site browses examples. For fine-tuning, pair programs with serverless SFT stacks once you define grading rubrics on exported meshes.

Install constraints builders hit early

The README is explicit about bpy wheels:

  • Python 3.12 is unsupported (no bpy wheel).
  • Intel Macs from bpy 5.2 onward should stay on Python 3.11.
  • CI runs against bpy 5.2 on Python 3.13.

If your agent sandbox is Node-only or Alpine musl, you will need a Linux glibc VM with Blender's Python module—similar friction to AnyPS5 native builds or GPU harness containers.

How sand3d fits explainx.ai's agent stack

sand3d does not replace LeRobot datasets on Lance or NVIDIA Cosmos factories. It is a authoring layer when the model must write geometry instead of retrieving meshes.

Teams building Snapchat-style AR or sim-ready props might chain:

  1. sand3d program from the agent
  2. GLB preview for humans
  3. URDF or USD for sim validation
  4. Promotion into a Lance table for training rows

Verb surface: what the API actually exposes

Sandflow deliberately avoids category magic like chair() or table(). Everything is built from profiles, solids, edits, frames, joints, and assembly verbs on the flat s3d namespace.

The README counts roughly:

table · 3 cols
FamilyExamplesCount listed
Profilesrect, slot, text, offset16
Solids and pathsextrude, loft, sweep, torus15
Editshole, pocket, fillet, shell15
Articulationjoint, pose, seatcore trio
Assemblygroup, export, fingerprint8

Materials and gears sit beside those families. The design goal is that an agent composes primitives rather than calling opaque generators—similar philosophically to MIT Isola's agent loops where structure beats hidden helpers.

Testing and determinism in CI

Because bpy ties sand3d to Blender's Python module, Sandflow runs CI on bpy 5.2 with Python 3.13. Deterministic rebuilds matter when you:

  1. Store programs in git and diff them in code review.
  2. Replay agent trajectories in eval harnesses.
  3. Compare mesh fingerprints with s3d.fingerprint style utilities documented in the README.

If your organization already runs Spaceship IDE on Cerebras for tight feedback loops, sand3d pairs well: short programs mean faster critique cycles before you export heavy GLB assets.

Who Sandflow is

The repository credits Thibault Neveu and Andrée Loy in CITATION.cff, with the public site at sandflow.ai. The project is young; treat release tags and CHANGELOG.md as your stability signal rather than a decade of semver history.

Limits and honesty

  • Category verbs are intentionally absent—no chair() helper; categories are programs.
  • Vendor token benchmarks need your own rerun on production parts.
  • IFC and USD dependencies pull in heavyweight tooling on CI runners.
  • The repo is young (late 2026); breaking changes may land despite CHANGELOG.md.

FAQ alignment with search intent

People who land on this page often ask whether sand3d replaces Blender. It does not: it generates bpy work through a constrained vocabulary. Others ask about robotics: prioritize URDF exports and joint tests in PyBullet before trusting decorative GLB.

Security and supply-chain notes

sand3d executes native bpy code. Treat agent-generated programs like any other arbitrary Python in your sandbox:

  • Run inside disposable VMs with no outbound mail or secret mounts.
  • Pin bpy versions and hash lockfiles in CI.
  • Scan exports before loading GLB in production viewers—mesh bombs are rare but cheap to guard against.

That posture matches how teams already isolate Codex sandboxes and Microsoft agent frameworks after typosquatting incidents.

When not to pick sand3d

Skip sand3d when you only need single-mesh props with no joints: a glTF from an artist may ship faster. Skip it when your runtime cannot install bpy (many serverless functions). Skip it when you need NURBS CAD exactness for machining—FeatureScript or native STEP workflows still win on tolerance stacks.

sand3d shines when an LLM must author and revise articulated assets repeatedly—robot cells, appliance demos, warehouse props—without ballooning token use. Start with the README bracket example, export one GLB, and only then scale to multi-joint assemblies your sim team can load. Sandflow's explorer and Hugging Face collection pages are the fastest way to sanity-check joint naming before you automate generation.

A practical evaluation plan

Before you adopt sand3d in a team workflow, run a small, honest bake-off. Pick ten parts your agents already generate today: a bracket, an enclosure, a gripper finger, a hinge, a shelf unit. Write each one twice, once in your current bpy or CadQuery style and once in sand3d, using the same model and the same prompt template.

Then measure four things:

  1. Prompt and completion tokens per part, including retries after export errors.
  2. First-pass success rate: how often the program exports without a traceback.
  3. Edit cost: how many tokens a follow-up change such as "make the holes 8 mm" needs.
  4. Sim load rate: whether the URDF opens in your simulator with the joint limits you intended.

Named parts help most in the edit step. A model can say "fillet the top edges of the plate" without recomputing coordinates, so revisions stay small and diffs stay readable in code review. If your numbers do not show a gain on your own catalog, the vendor chart does not matter for you. If they do, you have a concrete case for moving your asset pipeline to programs stored in git.

Related reading

  • Rust incremental agent rewrites with MCP parity
  • ForceHarness for frozen frontier models in robotics
  • NVIDIA Cosmos two-prompt physical AI datasets
  • Replica Skill for app reconstruction pipelines
  • What is MCP?
  • SoduWork multi-harness agent hub

Star counts and dataset names follow the Sandflow GitHub README as of November 19, 2026.

Spotted something out of date? Let us know.
Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

  • ✓ Free
  • ✓ One email a day, no spam
  • ✓ Unsubscribe anytime
Yash Thakker

Written by

Yash Thakker

Yash is an AI expert with over 300K learners. Join his workshops →

View Yash Thakker in People in AI →

Related posts

Nov 18, 2026

SoduWork: Self-Hosted Multi-Harness Agent Workspace for Teams

MDiRi open-sourced SoduWork, a self-hosted engine for teams and agents. You raise a request with acceptance criteria, assign a harness and model, run an independent AI review, and sign off. Pi, OpenCode, Codex, and six more harnesses share one plugin catalog.

Nov 16, 2026

ffmpeg-skill: Local Video Editing MCP for Claude Code, Cursor and Codex

ffmpeg-skill teaches coding agents a probe-edit-verify workflow with 42 Python FFmpeg tools and an MCP server. It runs offline with no API keys and trended past 6,000 GitHub stars in November 2026.

Nov 16, 2026

Qwen Code: Open-Source Terminal Coding Agent From Alibaba's QwenLM

Qwen Code is an open-source agent harness from QwenLM with terminal, desktop, web, and chat integrations. The repo crossed 30,000 GitHub stars this week with Agent Teams, Auto-Memory, and multi-provider routing.