diff --git a/README.md b/README.md
index 1d89c68..45df4ad 100644
--- a/README.md
+++ b/README.md
@@ -40,7 +40,7 @@ async with AsyncClient(token=os.environ["AA_TOKEN"]) as client:
         prompt=Prompt.from_text("Provide a short description of AI:"),
         maximum_tokens=64,
     )
-    response = await client.complete(request, model="luminous-base") 
+    response = await client.complete(request, model="luminous-base")
     print(response.completions[0].completion)
 ```
 
@@ -66,6 +66,27 @@ pip install aleph-alpha-client
 
 Get started using the client by first [creating an account](https://app.aleph-alpha.com/signup). Afterwards head over to [your profile](https://app.aleph-alpha.com/profile) to create an API token. Read more about how you can manage your API tokens [here](https://docs.aleph-alpha.com/docs/account).
 
+## Development
+
+For local development, start by creating a Python virtual environment as follows:
+
+```
+python3 -m venv venv
+. ./venv/bin/activate
+```
+
+Next, install the `test` and `dev` dependencies:
+
+```
+pip install -e ".[test,dev]"
+```
+
+Now you should be able to ...
+
+* run all the tests using `pytest` or, `pytest -k <test_name>` to run a specific test
+* typecheck the code and tests using `mypy aleph_alpha_client` resp. `mypy tests`
+* format the code using `black .`
+
 ## Links
 
 - [HTTP API Docs](https://docs.aleph-alpha.com/api/)
diff --git a/aleph_alpha_client/aleph_alpha_client.py b/aleph_alpha_client/aleph_alpha_client.py
index 7e1cc34..f3f0231 100644
--- a/aleph_alpha_client/aleph_alpha_client.py
+++ b/aleph_alpha_client/aleph_alpha_client.py
@@ -149,7 +149,7 @@ def __init__(
         request_timeout_seconds: int = DEFAULT_REQUEST_TIMEOUT,
         total_retries: int = 8,
         nice: bool = False,
-        verify_ssl = True,
+        verify_ssl=True,
     ) -> None:
         if host[-1] != "/":
             host += "/"
@@ -625,7 +625,7 @@ def __init__(
         request_timeout_seconds: int = DEFAULT_REQUEST_TIMEOUT,
         total_retries: int = 8,
         nice: bool = False,
-        verify_ssl = True,
+        verify_ssl=True,
     ) -> None:
         if host[-1] != "/":
             host += "/"
@@ -652,7 +652,7 @@ def __init__(
                 "User-Agent": "Aleph-Alpha-Python-Client-"
                 + aleph_alpha_client.__version__,
             },
-            connector=connector
+            connector=connector,
         )
 
     async def close(self):
diff --git a/tests/test_clients.py b/tests/test_clients.py
index 10da424..6f454ba 100644
--- a/tests/test_clients.py
+++ b/tests/test_clients.py
@@ -33,7 +33,12 @@ def test_nice_flag_on_client(httpserver: HTTPServer):
     ).respond_with_json(
         CompletionResponse(
             "model_version",
-            [CompletionResult(log_probs=[], completion="foo", )],
+            [
+                CompletionResult(
+                    log_probs=[],
+                    completion="foo",
+                )
+            ],
             num_tokens_prompt_total=2,
             num_tokens_generated=1,
         ).to_json()
diff --git a/tests/test_complete.py b/tests/test_complete.py
index a248ced..82a9a9a 100644
--- a/tests/test_complete.py
+++ b/tests/test_complete.py
@@ -128,28 +128,30 @@ def test_complete_with_echo(sync_client: Client, model_name: str, prompt_image:
     assert completion_result.log_probs is not None
     assert len(completion_result.log_probs) > 0
 
+
 @pytest.mark.system_test
 def test_num_tokens_prompt_total_with_best_of(sync_client: Client, model_name: str):
-    tokens = [49222, 2998] # Hello world
+    tokens = [49222, 2998]  # Hello world
     best_of = 2
     request = CompletionRequest(
-        prompt = Prompt.from_tokens(tokens),
-        best_of = best_of,
-        maximum_tokens = 1,
+        prompt=Prompt.from_tokens(tokens),
+        best_of=best_of,
+        maximum_tokens=1,
     )
 
     response = sync_client.complete(request, model=model_name)
     assert response.num_tokens_prompt_total == len(tokens) * best_of
 
+
 @pytest.mark.system_test
 def test_num_tokens_generated_with_best_of(sync_client: Client, model_name: str):
-    hello_world = [49222, 2998] # Hello world
+    hello_world = [49222, 2998]  # Hello world
     best_of = 2
     request = CompletionRequest(
-        prompt = Prompt.from_tokens(hello_world),
-        best_of = best_of,
-        maximum_tokens = 1,
-        tokens = True,
+        prompt=Prompt.from_tokens(hello_world),
+        best_of=best_of,
+        maximum_tokens=1,
+        tokens=True,
     )
 
     response = sync_client.complete(request, model=model_name)
@@ -157,4 +159,4 @@ def test_num_tokens_generated_with_best_of(sync_client: Client, model_name: str)
     assert completion_result.completion_tokens is not None
     number_tokens_completion = len(completion_result.completion_tokens)
 
-    assert response.num_tokens_generated == best_of * number_tokens_completion
\ No newline at end of file
+    assert response.num_tokens_generated == best_of * number_tokens_completion
diff --git a/tests/test_error_handling.py b/tests/test_error_handling.py
index 485f27e..783fb72 100644
--- a/tests/test_error_handling.py
+++ b/tests/test_error_handling.py
@@ -111,7 +111,13 @@ def expect_retryable_error(
 
 def expect_valid_completion(httpserver: HTTPServer) -> None:
     httpserver.expect_ordered_request("/complete").respond_with_json(
-        {"model_version": "1", "completions": [], "num_tokens_prompt_total": 0, "num_tokens_generated": 0})
+        {
+            "model_version": "1",
+            "completions": [],
+            "num_tokens_prompt_total": 0,
+            "num_tokens_generated": 0,
+        }
+    )
 
 
 def expect_valid_version(httpserver: HTTPServer) -> None:
diff --git a/tests/test_evaluate.py b/tests/test_evaluate.py
index 247c732..c6f6f6b 100644
--- a/tests/test_evaluate.py
+++ b/tests/test_evaluate.py
@@ -30,7 +30,6 @@ async def test_can_evaluate_with_async_client(
 
 @pytest.mark.system_test
 def test_evaluate(sync_client: Client, model_name: str):
-
     request = EvaluationRequest(
         prompt=Prompt.from_text("hello"), completion_expected="world"
     )
diff --git a/tests/test_prompt_template.py b/tests/test_prompt_template.py
index 36d8de1..db3e307 100644
--- a/tests/test_prompt_template.py
+++ b/tests/test_prompt_template.py
@@ -164,11 +164,12 @@ def test_to_prompt_works_with_tokens():
 
     assert prompt == user_prompt
 
+
 def test_to_prompt_resets_cache(prompt_image: Image):
     user_prompt = Prompt([prompt_image, Text.from_text("Cool"), prompt_image])
-    
+
     template = PromptTemplate("{{user_prompt}}")
 
     template.to_prompt(user_prompt=template.embed_prompt(user_prompt))
 
-    assert template.non_text_items == {} 
+    assert template.non_text_items == {}
diff --git a/tests/test_wildcard_import.py b/tests/test_wildcard_import.py
index fe9fffd..552df54 100644
--- a/tests/test_wildcard_import.py
+++ b/tests/test_wildcard_import.py
@@ -1,4 +1,5 @@
 from aleph_alpha_client import *
 
+
 def test_should_be_able_to_import_with_wildcard():
-    pass # Wildcard import can not go into the test itself
\ No newline at end of file
+    pass  # Wildcard import can not go into the test itself