SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-18 UTC

No new commits yet today

Open the update feed

ManiSkillmani-skill/ManiSkill

Provides a GPU-parallelized robot manipulation simulation and benchmarking environment,…

No ratings yet Rate this skill
Stars3.4k
Forks552
Watchers3.4k
Open Issues142

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/mani-skill/ManiSkill.git

OverviewOverview

Key Features

Provides a GPU-parallelized robot manipulation simulation and benchmarking environment, enabling researchers and developers to train and evaluate robot manipulation skills in virtual environments. Key capabilities include: 1. GPU-parallel simulation: GPU-accelerated physics simulation that runs many robot manipulation scenarios simultaneously, greatly reducing the time required for reinforcement learning training and policy evaluation; 2. Manipulation skill benchmarks: built-in standardized robot manipulation tasks and evaluation benchmarks for comparing different algorithms on grasping, moving, and assembly skills; 3. Reinforcement learning and robot learning support: interfaces for integrating with mainstream reinforcement learning frameworks, supporting training of robot manipulation policies in simulation and research on transfer to real-world scenarios.

Use Cases

reinforcement learning training for robot manipulation skills, embodied AI algorithm research and comparative experiments, simulation-based evaluation of robotic grasping and manipulation policies, GPU-accelerated large-scale simulation experiments.

Target Roles

AI / Algorithm Engineer, Hardware / Embedded Engineer, Test / QA Engineer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID296
Data sourceGitHub
Repositorymani-skill/ManiSkill
CategoryAI & Robotics / Robot Simulation & Reinforcement Learning
Primary languagePython
LicenseApache License 2.0
Default branchmain
GitHub repository ID520357130
Node IDR_kgDOHwQFCg
Rank#294 (position within the source ranking)
Site-wide popularity rank#360 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

01k2k3k4k2026-09-302026-10-102026-09-30 · 3,3672026-10-10 · 3,387
  • Now3,387
  • Previous point · 09-30 3,367
  • vs previous point +20
  • 2 data points 10 days
02004006002026-09-302026-10-102026-09-30 · 5502026-10-10 · 552
  • Now552
  • Previous point · 09-30 550
  • vs previous point +2
  • 2 data points 10 days

TimelineTimeline

Repository created2022-08-02 04:56:582022-08-02
Data last updated2026-10-26 11:56:0023 days ago
Last commit2026-08-04 16:38:183 months ago

CommitLatest commit

Committed by krmayn. Update Category: New Features & Capability Expansion. Commit details: [Feature] Demonstrate actor builder API in PushCube (#1479). This update introduces new capabilities and expands supported use cases.

62ff3a5 krmayn 2026-08-02