The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
ray-r-ren/agent-apprenticeship is accelerating — star growth is speeding up by +2.1/day (82nd percentile in the tracked cohort), on top of +0.1 stars/day.
Low breakout odds over the next 14 days, led by star acceleration (82th pctl) and momentum score (52th pctl). Confidence is high given the available history.
Transparent heuristic · logged for model training
Reconstructed from 182 snapshots — the time-series GitHub’s API doesn’t expose.
~11 forks/day, 15.8× the trailing baseline.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/ray-r-ren/agent-apprenticeship)Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.