LW-BenchHub is a unified benchmark hub built on Isaac Lab–Arena for embodied AI, providing consistent interfaces, realistic environments, multi-robot support, and large-scale evaluation. It includes Lightwheel-Libero-Tasks and Lightwheel-RoboCasa-Tasks with 268 tasks, reproducible RL configs, and a full pipeline for benchmarking robot policies.
active 2025-12-09 → 2026-05-25 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 168 days from 2025-12-09 to 2026-05-25. Pushes: 21 total, peak 3 in a day. Pull requests: 3 total, peak 1 in a day. Issues: 3 total, peak 1 in a day. Comments: 7 total, peak 3 in a day. Stars: 34 total, peak 3 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| Leon-Shang | 16 | 16 | 0 | 0 |
| yjmade | 4 | 3 | 1 | 0 |
| yueduduo | 3 | 0 | 0 | 3 |
| qwerty863 | 3 | 0 | 0 | 2 |
| baz1boy | 2 | 1 | 0 | 1 |
| qx13 | 1 | 0 | 0 | 0 |
| zsy1987 | 1 | 1 | 0 | 0 |
| Papaercold | 1 | 0 | 1 | 0 |
| chuchen0210 | 1 | 0 | 0 | 1 |
| kekekek111 | 1 | 0 | 0 | 0 |
| alexander-camuto | 1 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#40kekekek1112026-04-16 21:39Question about joint_4 being fixed in PiPER teleoperation data collection
- Pull request#38Papaercold2026-04-14 20:31
- Issue comment#37baz1boy2026-03-24 12:15How to configure the intial pose of robot for each task when add new embodiment into the LW-BenchHub
- Issue comment#31chuchen02102026-01-26 06:43Cannot run "Teleoperation Data Collection" in Quick Start
- Issue comment#31qwerty8632026-01-17 09:28Cannot run "Teleoperation Data Collection" in Quick Start
- Issue comment#31qwerty8632026-01-17 08:54Cannot run "Teleoperation Data Collection" in Quick Start
- Issue comment#31yueduduo2026-01-16 11:31Cannot run "Teleoperation Data Collection" in Quick Start
- Issue comment#29yueduduo2026-01-16 11:27`cfg.headless` is being implicitly overwritten by AppLauncher defaults in `export_env_for_envhub `
- Issue comment#28yueduduo2026-01-16 11:25Cannot download Miniconda from internal Artifactory (base.dockerfile)
- Issue#31qwerty8632026-01-09 06:47Cannot run "Teleoperation Data Collection" in Quick Start
- Pull request#30alexander-camuto2026-01-07 00:42
- Issue#28qx132025-12-16 19:08Cannot download Miniconda from internal Artifactory (base.dockerfile)
- Pull request#26yjmade2025-12-09 02:56
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 34 stars here means stars gained during the window, not the repo's star count.