NVlabs/ASPIRE

★903PythonApache-2.0⑂ 78Issue 9Updated Oct 16, 2026

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.

AI agents

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)
DateDaily
Oct 21, 2026
python #18 +65
Oct 19, 2026
python #9 +94

Created Jul 9, 2026 · First on trending Oct 19, 2026

Other notable repositories in the same category (AI agents)

See all AI agents repositories →

Get the weekly digest by email

Every Monday: the repositories that grew most last week, and how the buzz spread between the global and Japanese-language web. Unsubscribe any time. See the privacy and ad policy for how we handle your address.