diff --git a/packages.yml b/packages.yml
index 3d4b7c1f06..7cf9313497 100644
--- a/packages.yml
+++ b/packages.yml
@@ -797,3 +797,5 @@ packages:
   js: "n/a"
   downloads: 188
   downloads_updated_at: '2026-06-15T00:31:43.789982+00:00'
+- name: langchain-aneforge
+  repo: sbryngelson/langchain-aneforge
diff --git a/src/oss/python/integrations/providers/aneforge.mdx b/src/oss/python/integrations/providers/aneforge.mdx
new file mode 100644
index 0000000000..e35b46545f
--- /dev/null
+++ b/src/oss/python/integrations/providers/aneforge.mdx
@@ -0,0 +1,35 @@
+---
+title: "ANEForge"
+description: "Run LangChain embeddings on the Apple Neural Engine via ANEForge."
+---
+
+[`langchain-aneforge`](https://github.com/sbryngelson/langchain-aneforge) runs a
+sentence-embedding model on the Apple Neural Engine through
+[ANEForge](https://github.com/sbryngelson/ANEForge), with no CoreML. It runs on
+Apple Silicon macOS.
+
+## Installation and setup
+
+<CodeGroup>
+```bash pip
+pip install langchain-aneforge
+```
+
+```bash uv
+uv add langchain-aneforge
+```
+</CodeGroup>
+
+## Embeddings
+
+`ANEEmbeddings` is a `langchain_core.embeddings.Embeddings` that encodes on the
+Neural Engine. The pooling mode and normalize flag are read from each model's
+sentence-transformers config, so mean-pooled (MiniLM, E5) and cls-pooled (BGE, GTE)
+models both produce correct vectors.
+
+```python
+from langchain_aneforge import ANEEmbeddings
+
+embeddings = ANEEmbeddings(model="sentence-transformers/all-MiniLM-L6-v2")
+vector = embeddings.embed_query("the Apple Neural Engine runs networks at low power")
+```