diff --git a/plots/bar-categorical/implementations/letsplot.py b/plots/bar-categorical/implementations/letsplot.py
new file mode 100644
index 0000000000..49902de71f
--- /dev/null
+++ b/plots/bar-categorical/implementations/letsplot.py
@@ -0,0 +1,44 @@
+""" pyplots.ai
+bar-categorical: Categorical Count Bar Chart
+Library: letsplot 4.8.2 | Python 3.13.11
+Quality: 91/100 | Created: 2025-12-30
+"""
+
+import numpy as np
+import pandas as pd
+from lets_plot import *  # noqa: F403
+from lets_plot.export import ggsave as export_ggsave
+
+
+LetsPlot.setup_html()  # noqa: F405
+
+# Data - raw categorical values (counts computed automatically by geom_bar)
+np.random.seed(42)
+categories = ["Apples", "Bananas", "Oranges", "Grapes", "Mangoes"]
+weights = [0.25, 0.20, 0.22, 0.18, 0.15]
+n_samples = 200
+
+df = pd.DataFrame({"fruit": np.random.choice(categories, size=n_samples, p=weights)})
+
+# Plot - geom_bar computes counts automatically (no stat='identity')
+plot = (
+    ggplot(df, aes(x="fruit"))  # noqa: F405
+    + geom_bar(fill="#306998", color="#1a3a54", size=0.5, alpha=0.9)  # noqa: F405
+    + labs(  # noqa: F405
+        x="Fruit Type", y="Count", title="bar-categorical · letsplot · pyplots.ai"
+    )
+    + ggsize(1600, 900)  # noqa: F405
+    + theme_minimal()  # noqa: F405
+    + theme(  # noqa: F405
+        plot_title=element_text(size=24, face="bold"),  # noqa: F405
+        axis_title=element_text(size=20),  # noqa: F405
+        axis_text=element_text(size=16),  # noqa: F405
+        axis_text_x=element_text(angle=0),  # noqa: F405
+        panel_grid_major_x=element_blank(),  # noqa: F405
+        panel_grid_minor=element_blank(),  # noqa: F405
+    )
+)
+
+# Save as PNG (scale 3x for 4800x2700 px) and HTML
+export_ggsave(plot, filename="plot.png", path=".", scale=3)
+export_ggsave(plot, filename="plot.html", path=".")
diff --git a/plots/bar-categorical/metadata/letsplot.yaml b/plots/bar-categorical/metadata/letsplot.yaml
new file mode 100644
index 0000000000..fb6c7d812e
--- /dev/null
+++ b/plots/bar-categorical/metadata/letsplot.yaml
@@ -0,0 +1,25 @@
+library: letsplot
+specification_id: bar-categorical
+created: '2025-12-30T11:24:11Z'
+updated: '2025-12-30T11:32:01Z'
+generated_by: claude-opus-4-5-20251101
+workflow_run: 20595340647
+issue: 0
+python_version: 3.13.11
+library_version: 4.8.2
+preview_url: https://storage.googleapis.com/pyplots-images/plots/bar-categorical/letsplot/plot.png
+preview_thumb: https://storage.googleapis.com/pyplots-images/plots/bar-categorical/letsplot/plot_thumb.png
+preview_html: https://storage.googleapis.com/pyplots-images/plots/bar-categorical/letsplot/plot.html
+quality_score: 91
+review:
+  strengths:
+  - Clean implementation following ggplot2 grammar of graphics
+  - Automatic count computation using geom_bar() without stat=identity
+  - Well-sized text elements (24pt title, 20pt axis labels, 16pt tick text) following
+    library guidelines
+  - Good use of theme_minimal() with appropriate grid customization
+  - Proper figure sizing (1600x900 with scale=3 for 4800x2700 output)
+  weaknesses:
+  - Does not leverage lets-plot interactive features (tooltips, hover effects) that
+    distinguish it from plotnine
+  - Data context is generic; could use a more specific real-world scenario