# cobusgreyling/loop-engineering

> A pattern library, starters and CLI tools for loop engineering: designing loops where AI coding agents discover work in a repo, act on it and verify results. Aimed at developers who want to automate routine codebase chores with Claude Code, Codex, Grok and GitHub Actions.

- Magnitude: 2.3 out of 10 — Steady
- Stars: 11,564 total · +10 stars measured 2026-10-16, 00:10–23:36 UTC
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2026-06-09 · Last push: 2026-10-16
- GitHub: https://github.com/cobusgreyling/loop-engineering · Homepage: https://cobusgreyling.github.io/loop-engineering/ · Page: https://gitnova.dev/en/r/cobusgreyling/loop-engineering

## Useful for

- Set up a daily-triage loop to watch issues, CI and dependencies in a repo
- Configure a PR Babysitter loop to babysit pull requests automatically
- Estimate loop cost and autonomy level with the loop cost command

## Why it’s here

- Star-counter measurements on 2026-10-16 (UTC), 00:10–23:36: 11554 → 11564 stars (+10). This is the change over that interval.
- About 34 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1,594
- Issues and pull requests: 671
- Watchers: 73
- Average over the last week: 18 per day
- Usual pace: 12 per day
- Latest release: v1.6.0 (2026-07-20)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 41, 8, 6, 6, 9, 7, 9, 11, 4, 7, 38, 20, 13, 7, 20, 17, 6, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

10-03 1.2, 10-04 1.2, 10-05 1.5, 10-06 1.3, 10-07 1.4, 10-08 1.4, 10-09 1.0, 10-10 1.9, 10-11 2.7, 10-12 2.3, 10-13 2.0, 10-14 1.8, 10-15 2.4, 10-16 2.4

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-16 23:43 UTC, updated every 30 minutes.