diff --git a/_posts/2024-05-22-swe-bench-lite.md b/_posts/2024-05-22-swe-bench-lite.md
index 3bf0a08d2..dac61a3d4 100644
--- a/_posts/2024-05-22-swe-bench-lite.md
+++ b/_posts/2024-05-22-swe-bench-lite.md
@@ -67,6 +67,8 @@ The held out "acceptance tests" were *only* used
 after benchmarking to compute statistics on which problems aider
 correctly resolved.
 
+The [full harness to run aider on SWE Bench Lite is available on GitHub](https://github.com/paul-gauthier/aider-swe-bench).
+
 The benchmarking process was similar to how a developer might use aider to
 resolve a GitHub issue: