diff --git a/README.md b/README.md
index 7953fd3a0..318632989 100644
--- a/README.md
+++ b/README.md
@@ -783,5 +783,10 @@ docker run --gpus all -v /path/to/models:/models local/llama.cpp:light-cuda -m /
 
 ### Docs
 
-- [GGML tips & tricks](https://github.com/ggerganov/llama.cpp/wiki/GGML-Tips-&-Tricks)
+- [main](./examples/main/README.md)
+- [server](./examples/server/README.md)
+- [embd-input](./examples/embd-input/README.md)
+- [jeopardy](./examples/jeopardy/README.md)
+- [BLIS](./docs/BLIS.md)
 - [Performance troubleshooting](./docs/token_generation_performance_tips.md)
+- [GGML tips & tricks](https://github.com/ggerganov/llama.cpp/wiki/GGML-Tips-&-Tricks)