Skip to content

CubeLoop — a Pythonic, async-native agent harness core designed for high performance, readability, and production-grade persistence.

docs: update DeepWiki badge to official badge.svg

xf gong59bb36cba4ce
diff --git a/README.md b/README.md
index 7494306..5b064cc 100644
--- a/README.md
+++ b/README.md
@@ -8,7 +8,7 @@
[![Python](https://img.shields.io/pypi/pyversions/cubepi)](https://pypi.org/project/cubepi/)
[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT)
[![Docs](https://img.shields.io/badge/docs-cubepi.ai-blue)](https://cubepi.ai)
-[![Ask DeepWiki](https://img.shields.io/badge/Ask-DeepWiki-1f6feb)](https://deepwiki.com/cubeplexai/cubepi)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/cubeplexai/cubepi)
[![skills.sh](https://skills.sh/b/cubeplexai/cubepi)](https://skills.sh/cubeplexai/cubepi)
CubePi is a Pythonic, async-native agent framework designed for high performance, readability, and production-grade persistence. It provides a leaner alternative to graph-based agent runtimes by modeling agent logic as a linear while loop that developers can easily trace and debug.