CrestingRadar

AI agent

fable-method

The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.

Rank
#4 of 2,409
Stars
117 +77/wk
On radar
since 2026-07-09

Momentum

rate of rise, not size · recomputes hourly

85.7
24h· new7d· new

Collecting daily history; the trend chart appears after 3 days on the radar

Why it's ranked

fable-method is an AI agent ranked #4 of 2,409 on the Cresting momentum radar, with a score of 85.7. It has 117 GitHub stars, +77 in the last 7 days, and has been tracked since 2026-07-09.

Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →

Velocity (weighted, cohort-normalized)0.959
Recency boost0.774
Signal decay0.983
Corroboration1.000
Quality gate1.000

Raw signals (30 days)

github · forks+11 in window · 15 latest · 2 snapshots
github · stars+77 in window · 117 latest · 2 snapshots

Related ai agents