diff --git a/README.md b/README.md
index 70f053f..254cd62 100644
--- a/README.md
+++ b/README.md
@@ -19,6 +19,8 @@ The goal is:
 
 Note: Be warned! It was hacked in a weekend, and it's just an experiment to see what can be done with local LLMs. 
 
+![Screenshot from 2023-08-05 22-40-40](https://github.com/mudler/LocalAGI/assets/2420543/fc9d3c5d-d522-467b-9a84-fea18a78e75f)
+
 ## Demo
 
 Search on internet (interactive mode)
@@ -178,4 +180,4 @@ docker-compose run -v main.py:/app/main.py -i --rm localagi
 - With superhot models looses its magic, but maybe suitable for search
 - Context size is your enemy. `--postprocess` some times helps, but not always
 - It can be silly!
-- It is slow on CPU, don't expect `7b` models to perform good, and `13b` models perform better but on CPU are quite slow.
\ No newline at end of file
+- It is slow on CPU, don't expect `7b` models to perform good, and `13b` models perform better but on CPU are quite slow.