diff --git a/README.md b/README.md
index cd1827e..8d92cb3 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
# Dervish MCP
-
+
**Dervish** infers **regular expression grammars** from example sequences using the BEX family of algorithms. Given a set of example sequences (strings over some alphabet), it learns a compact regular expression that captures the general pattern.
@@ -15,6 +15,8 @@ Dervish replaces both with a **one-call MCP tool**: pass your sequences, get bac
**Without Dervish:** token cost scales linearly with examples. **With Dervish:** one compact grammar describes them all — a ~60–200 token rule instead of thousands of tokens of raw examples.
+
+
## MCP Server
The primary interface is a **Model Context Protocol (MCP)** server. Connect any MCP-compatible client (pi.dev, opencode, vibe, etc.) and get grammar inference as a tool:
diff --git a/SHOWCASE.md b/SHOWCASE.md
index f74f3f0..d43b05b 100644
--- a/SHOWCASE.md
+++ b/SHOWCASE.md
@@ -1,6 +1,6 @@
# Dervish — Showcase
-
+
Infer the **unwritten convention** from existing examples. Given N example
sequences, produce a ~100-char grammar that captures the structural
diff --git a/blog_post.md b/blog_post.md
index 03bb7a1..b330c7c 100644
--- a/blog_post.md
+++ b/blog_post.md
@@ -1,6 +1,6 @@
# Dervish: Discovering Unwritten Conventions with Grammar Inference
-
+
**How we turned 36 Ansible roles into a 200-character grammar — and why
it matters for LLM agents.**
diff --git a/dervish-logo.png b/dervish-logo.png
new file mode 100644
index 0000000..fe496eb
Binary files /dev/null and b/dervish-logo.png differ
diff --git a/dervish.gif b/dervish.gif
index fe496eb..19d6e92 100644
Binary files a/dervish.gif and b/dervish.gif differ