Skip to content

Building AI agents, atomically

Update README.md

Kenny Vaneetvelde2ebf0740c481
diff --git a/README.md b/README.md
index a2aac3b..2a9d5b8 100644
--- a/README.md
+++ b/README.md
@@ -1,13 +1,16 @@
# Atomic Agents
+
+<img src="./.assets/logo.png" alt="Atomic Agents" width="350"/>
+
+---
+
### [Watch the Overview Video](https://www.youtube.com/watch?v=Sp30YsjGUW0)
<a href="https://www.youtube.com/watch?v=Sp30YsjGUW0" target="_blank">
- <img src="./.assets/video-thumbnail.png" alt="Watch the video" height="200"/>
+ <img src="./.assets/video-thumbnail.png" alt="Watch the video" width="350"/>
</a>
---
-<img src="./.assets/logo.png" alt="Atomic Agents" width="600"/>
-
[![PyPI version](https://badge.fury.io/py/atomic-agents.svg)](https://badge.fury.io/py/atomic-agents)
The Atomic Agents framework is designed to be modular, extensible, and easy to use. Its main goal is to eliminate redundant complexity, unnecessary abstractions, and hidden assumptions while still providing a flexible and powerful platform for building AI applications through atomicity. The framework provides a set of tools and agents that can be combined to create powerful applications. It is built on top of [Instructor](https://github.com/jxnl/instructor) and leverages the power of [Pydantic](https://docs.pydantic.dev/latest/) for data and schema validation and serialization.