Polish lifecycle figure and README header
Browse filesReorders the README top section to match the atlas-style organization and replaces the lifecycle figure with a cleaner polished SVG.
- README.md +18 -3
- assets/loop-lifecycle.svg +97 -72
README.md
CHANGED
|
@@ -11,14 +11,29 @@ tags:
|
|
| 11 |
- software-engineering
|
| 12 |
---
|
| 13 |
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
<p align="center">
|
| 17 |
<img src="assets/awesome-loop-engineering-logo.svg" alt="Awesome Loop Engineering logo" width="112">
|
| 18 |
</p>
|
| 19 |
|
| 20 |
<p align="center">
|
| 21 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
</p>
|
| 23 |
|
| 24 |
<p align="center">
|
|
@@ -35,7 +50,7 @@ tags:
|
|
| 35 |
<a href="https://huggingface.co/cy0307/awesome-loop-engineering">Hugging Face mirror</a>
|
| 36 |
</p>
|
| 37 |
|
| 38 |
-
|
| 39 |
|
| 40 |
Prompt engineering improves what you ask the model. Context engineering improves what the model can see. Harness engineering improves the tools, permissions, sandboxes, and checks around one agent run. **Loop Engineering sits above all three**: it is the emerging AI and coding-agent practice of moving from manually prompting agents turn by turn to designing loops that do the prompting, supervision, verification, state updates, and re-triggering for you.
|
| 41 |
|
|
|
|
| 11 |
- software-engineering
|
| 12 |
---
|
| 13 |
|
| 14 |
+
<p align="center">
|
| 15 |
+
<img src="assets/awesome-loop-engineering-cover.png" alt="Awesome Loop Engineering cover" width="100%">
|
| 16 |
+
</p>
|
| 17 |
+
|
| 18 |
+
# Awesome Loop Engineering
|
| 19 |
|
| 20 |
<p align="center">
|
| 21 |
<img src="assets/awesome-loop-engineering-logo.svg" alt="Awesome Loop Engineering logo" width="112">
|
| 22 |
</p>
|
| 23 |
|
| 24 |
<p align="center">
|
| 25 |
+
Curated resources and practical patterns for designing recurring, stateful, verified AI-agent loops.
|
| 26 |
+
</p>
|
| 27 |
+
|
| 28 |
+
<p align="center">
|
| 29 |
+
<a href="https://github.com/sindresorhus/awesome"><img src="https://awesome.re/badge.svg" alt="Awesome"></a>
|
| 30 |
+
<a href="https://github.com/ChaoYue0307/awesome-loop-engineering/actions/workflows/quality.yml"><img src="https://img.shields.io/github/actions/workflow/status/ChaoYue0307/awesome-loop-engineering/quality.yml?branch=main&label=validate" alt="validate"></a>
|
| 31 |
+
<a href="https://chaoyue0307.github.io/awesome-loop-engineering/"><img src="https://img.shields.io/badge/project-site-38bdf8" alt="project site"></a>
|
| 32 |
+
<a href="https://huggingface.co/cy0307/awesome-loop-engineering"><img src="https://img.shields.io/badge/Hugging%20Face-mirror-ffcc4d" alt="Hugging Face mirror"></a>
|
| 33 |
+
<img src="https://img.shields.io/badge/resources-250%2B-a78bfa" alt="resources">
|
| 34 |
+
<img src="https://img.shields.io/badge/patterns-15-38bdf8" alt="patterns">
|
| 35 |
+
<a href="LICENSE"><img src="https://img.shields.io/badge/license-CC0--1.0-64748b" alt="license"></a>
|
| 36 |
+
<a href="CONTRIBUTING.md"><img src="https://img.shields.io/badge/PRs-welcome-22c55e" alt="PRs welcome"></a>
|
| 37 |
</p>
|
| 38 |
|
| 39 |
<p align="center">
|
|
|
|
| 50 |
<a href="https://huggingface.co/cy0307/awesome-loop-engineering">Hugging Face mirror</a>
|
| 51 |
</p>
|
| 52 |
|
| 53 |
+
Awesome Loop Engineering is a curated, implementation-oriented field guide to **Loop Engineering**: the layer above prompt, context, and harness engineering for designing recurring AI-agent systems.
|
| 54 |
|
| 55 |
Prompt engineering improves what you ask the model. Context engineering improves what the model can see. Harness engineering improves the tools, permissions, sandboxes, and checks around one agent run. **Loop Engineering sits above all three**: it is the emerging AI and coding-agent practice of moving from manually prompting agents turn by turn to designing loops that do the prompting, supervision, verification, state updates, and re-triggering for you.
|
| 56 |
|
assets/loop-lifecycle.svg
CHANGED
|
|
|
|