dimensionalOS / dimensionalOS/dimos

PimSim: executable worlds and physical-agent CI

Open
#2,894 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

this week
Dominant language
Python
Stars
4.5k
Forks
808
Avg merge
3d 5h
Merged PRs (30d)
233

Description

Build the standard simulation and evaluation platform beneath ordinary DimOS applications.

Two product loops

  1. World construction: authored, procedural, or captured sources compile into validated executable scene packages.
  2. Physical CI: unchanged DimOS agents and skills run in those worlds and are verified, compared, and promoted to hardware.

Hyper-realistic means

Gaussian splats provide camera appearance. Clean cooked meshes provide collision, navigation, raycasting, contact, and MuJoCo physics. Semantics, devices, calibration, and alignment stay explicit.

Roadmap

  1. Executable scene compiler
  2. Unreal-to-splat and cooked-physics pipeline
  3. Procedural scene families
  4. Task, skill, trace, and promotion contracts
  5. xArm physical pick/place gate
  6. Flagship long-horizon mobile-manipulation mission
  7. Real deployment-site capture and sim-real regression loop

Broad robot coverage, product UX, and training scale follow these gates.


Synced from DIM-1188 by mustafa

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or entry points are named. Start by reviewing the linked DIM-1188 issue and the repository's existing simulation and CI structure, then narrow the roadmap to one explicitly scoped gate. Done should be defined by an implemented gate with a verifiable simulation or physical-agent evaluation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, unreal-engine
Domain
computer-graphics, robotics, testing-qa
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.