NVlabs/ASPIRE
ASPIRE: Agentic /Skills Discovery for Robotics
NVIDIA's robot skill repo where LLM agents replace gradient descent — ASPIRE reframes continual robot learning as agents discovering and refining a repository of sensorimotor skills instead of training neural weights. v1.0 reports 99% success on 80 LIBERO-Pro/Robosuite/BEHAVIOR-1K tasks and a Rubik's Cube solve, useful for robotics researchers exploring LLM-agent-driven skill learning.
Metrics
Relative growth (7d)+11%Growth over the last 7 days relative to size
Acceleration-81%Change in growth pace from the week before
Attention39The three metrics scaled to 0–100 and combined
Retention can be computed 30 days after a repository first trends (it isn't shown until then). See About for how each metric is defined.
Star growth and Trending appearances (last 30 days)
First listed+141★/dayDaily
Sep 30, 2026Oct 29, 2026
Bands mark days on the trending list (darker = higher rank)
Daily trending ranks as a table (2 days)
| Date | Daily |
|---|---|
| Oct 21, 2026 | python #18 +65 |
| Oct 19, 2026 | python #9 +94 |
Created Jul 9, 2026 · First on trending Oct 19, 2026