Niches · 3D worlds

Make test environments for a robot or simulator

No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.

0companies, full fit
2companies, fit with a limit
2companies carry the tag
11share of the category's work
4first-hand accounts

What counts as done

A splat plus a collider mesh at metric scale that the simulator loads without hand alignment, with surfaces such as the floor identifiable, produced for many scenes at a known cost per scene.

How agents ask for it: test the robot in a cluttered kitchen with a dog, generate 50 warehouse scenes for evaluation, a simulation world from this photo of the site

Does the job, with a limit 2

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
SpAItial API (Echo) C
SpAItial Ltd
Splat plus mesh and mesh-simplified collision exports, a floor-plan render, and a fixed 160 credits a generated scene with 10 creates a minute. Metric scale is stated only for Echo-3 captures, so generated scenes need the hand alignment acc-19 automated. source
World Labs World API (Marble) D
World Labs Technologies, Inc.
Splat plus a 100k to 200k triangle collider at a stated metric scale, ground plane given, fixed price per marble-1.1 scene and 60 starts an hour by default. Alignment transform is the caller's job, and accounts doubt the physical validity of the floors (acc-07, acc-08). source

What stops agents finishing

  • collider has to be lined up by hand in the existing chain (acc-14)
  • visually plausible scenes that fail physically on real hardware (acc-07)
  • no statement on the World API's future after the AMD acquisition

Around it

Before: inference.chat-completion. After: gpu-compute.run-job.

Where this comes from

Weight 11 of 100 in 3D worlds: 4 of 36 links: a robotics simulator's integration plan on GitHub, a research comparison against Marble, and two HN comments doubting physical fidelity

The same as data: /api/v1/use-cases/3d-worlds.sim-environment.json, or the MCP tool get_use_case with id 3d-worlds.sim-environment. Other jobs in this category: /api/v1/niches?category=3d-worlds.

Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.