AI agent
loop.js
A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.
- Rank
- #4 of 2,484
- Stars
- 105★ +74/wk
- On radar
- since 2026-07-11
Momentum
rate of rise, not size · recomputes hourly
82.1
24h· new7d· new
Hover the chart for daily values
Why it's ranked
loop.js is an AI agent ranked #4 of 2,484 on the Cresting momentum radar, with a score of 82.1. It has 105 GitHub stars, +74 in the last 7 days, and has been tracked since 2026-07-11.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.929 |
| Recency boost | 0.748 |
| Signal decay | 0.983 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+0 in window · 0 latest · 4 snapshots
github · stars+74 in window · 105 latest · 4 snapshots
Related ai agents
- WorkBuddyGuideA practical, open-source guide to mastering WorkBuddy through real-world workflows.开源的 WorkBuddy 实战蓝皮书：教程、真实工作流、Skills、MCP、自动化与多智能体实践。#1 · 630★
- clodex-ideLocal-first, zero-trust agentic IDE for verifiable autonomous software development.#2 · 700★
- pilotfishMulti-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.#5 · 438★
- vox-directorTurn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.#6 · 123★
- fable-methodThe Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.#7 · 556★