diff --git a/ann_benchmarks/algorithms/deeplake/Dockerfile b/ann_benchmarks/algorithms/deeplake/Dockerfile
new file mode 100644
index 000000000..224022dee
--- /dev/null
+++ b/ann_benchmarks/algorithms/deeplake/Dockerfile
@@ -0,0 +1,8 @@
+FROM ann-benchmarks
+ENV BUGGER_OFF=true
+ENV ACTIVELOOP_TOKEN=eyJhbGciOiJIUzUxMiIsImlhdCI6MTY4MTI4Mzc3NywiZXhwIjoxNzEyOTA2MDk5fQ.eyJpZCI6Im5vdGlmeSJ9.C3zTjQODfq0TUhkdRye639aKJ0FOanZuCwL2ks2NiKXJ6YecYVMBrdFu3AabGsk7iuS-ELtQYp7WxITv76hcSg
+ENV ACTIVELOOP_ORG=notify
+
+RUN apt-get install -y python-setuptools python-pip
+RUN pip3 install deeplake
+RUN python3 -c 'import deeplake'
diff --git a/ann_benchmarks/algorithms/deeplake/config.yml b/ann_benchmarks/algorithms/deeplake/config.yml
new file mode 100644
index 000000000..6ccf2eea1
--- /dev/null
+++ b/ann_benchmarks/algorithms/deeplake/config.yml
@@ -0,0 +1,45 @@
+float:
+  any:
+  - base_args: ['@metric']
+    constructor: DeeplakeHnsw
+    disabled: false
+    docker_tag: ann-benchmarks-deeplake
+    module: ann_benchmarks.algorithms.deeplake
+    name: deeplake
+    run_groups:
+      M-12:
+        arg_groups: [{M: 12, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-16:
+        arg_groups: [{M: 16, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-24:
+        arg_groups: [{M: 24, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-36:
+        arg_groups: [{M: 36, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-4:
+        arg_groups: [{M: 4, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-48:
+        arg_groups: [{M: 48, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-64:
+        arg_groups: [{M: 64, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-8:
+        arg_groups: [{M: 8, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-96:
+        arg_groups: [{M: 96, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
diff --git a/ann_benchmarks/algorithms/deeplake/module.py b/ann_benchmarks/algorithms/deeplake/module.py
new file mode 100644
index 000000000..6a8bb0039
--- /dev/null
+++ b/ann_benchmarks/algorithms/deeplake/module.py
@@ -0,0 +1,60 @@
+import deeplake
+import numpy as np
+import os
+import random
+import string
+from ..base.module import BaseANN
+
+
+# Class using the Deeplake implementation of an HNSW index for nearest neighbor
+# search over data points in a high dimensional vector space.
+
+class DeeplakeHnsw(BaseANN):
+    def __init__(self, metric, param, enable_normalize = True, dimension = None):
+        if metric not in ("angular", "euclidean"):
+            raise NotImplementedError(f"Deeplake doesn't support metric {metric}")
+        if metric == "angular":
+            self.metric = "cosine_similarity"
+        else:
+            self.metric = "l2_norm"
+        self.param = param
+        self._ef_construction = param.get("efConstruction", 200)
+        self._m = param.get("M", 16)
+        self.dimension = dimension
+        suffix = ''.join(random.choice(string.ascii_uppercase + string.digits) for _ in range(8)) 
+        self.local_path = f"ANN_benchmarks-embeddings_{suffix}"
+        self.name = "deeplake"
+        self.token = os.environ.get('ACTIVELOOP_TOKEN')
+        self.org = os.environ.get('ACTIVELOOP_ORG')
+
+    def __del__(self):
+        self.freeIndex()
+
+    def fit(self, X):
+        self.ds = deeplake.dataset(self.local_path, overwrite=True, token=self.token, org_id=self.org)
+        self.ds.create_tensor("embedding", htype="embedding", dtype="float32", create_shape_tensor=False, create_id_tensor=False)
+        self.ds.embedding.extend(X)
+        self.ds.embedding.create_vdb_index("hnsw_1", distance=self.metric, additional_params={
+            "efConstruction": self._ef_construction, "M": self._m
+        })
+        self.index = self.ds.embedding.load_vdb_index("hnsw_1")
+
+    def set_query_arguments(self, ef):
+        self.index.set_search_params(ef=ef)
+
+    def query(self, v, n):
+        v_float = np.array(v).astype(np.float32)
+        view =  self.index.search_knn(v_float, n)
+        return view.indices
+
+    def __str__(self):
+        return f"Deeplake(m={self._m}, ef_construction={self._ef_construction})"
+
+    def freeIndex(self):
+        if hasattr(self, 'index'):
+            del self.index
+        if hasattr(self, 'ds'):
+            del self.ds
+            deeplake.delete(self.local_path)
+        if os.path.isfile(f"/tmp/{self.local_path}/embedding"):
+            os.remove(f"/tmp/{self.local_path}/embedding")