diff --git a/.gitignore b/.gitignore
index 0eeba76..8c447dc 100644
--- a/.gitignore
+++ b/.gitignore
@@ -3,4 +3,8 @@ data/
 .DS_store
 __pycache__
 Monoloco/*.pyc
-.pytest*
\ No newline at end of file
+.pytest*
+dist/
+build/
+*.egg-info
+
diff --git a/README.md b/README.md
index 6bf9cb3..d056931 100644
--- a/README.md
+++ b/README.md
@@ -26,13 +26,23 @@ A video with qualitative results is available on [YouTube](https://www.youtube.c
 # Setup
 
 ### Install
+Python 3 is required. Python 2 is not supported. 
+Do not clone this repository and make sure there is no folder named monoloco in your current directory.
+
+`pip install monoloco`
+
+Live demo is available, we recommend to try our **Webcam** functionality. More info in the webcam section.
+
+
+For development of the monoloco source code itself, you need to clone this repository and then:
+```
+pip install openpifpaf nuscenes-devkit tabulate
+```
 Python 3.6 or 3.7 is required for nuScenes development kit. Python 3 is required for openpifpaf. 
 All details for Pifpaf pose detector at [openpifpaf](https://github.com/vita-epfl/openpifpaf).
 
 
-```
-pip install openpifpaf nuscenes-devkit tabulate
-```
+
 ### Data structure
 
     Data         
diff --git a/monoloco/__init__.py b/monoloco/__init__.py
index e69de29..451d4a2 100644
--- a/monoloco/__init__.py
+++ b/monoloco/__init__.py
@@ -0,0 +1,4 @@
+
+"""Open implementation of MonoLoco."""
+
+__version__ = '0.4.0'
diff --git a/setup.py b/setup.py
new file mode 100644
index 0000000..2bf0100
--- /dev/null
+++ b/setup.py
@@ -0,0 +1,36 @@
+from setuptools import setup
+
+# extract version from __init__.py
+with open('monoloco/__init__.py', 'r') as f:
+    VERSION_LINE = [l for l in f if l.startswith('__version__')][0]
+    VERSION = VERSION_LINE.split('=')[1].strip()[1:-1]
+
+setup(
+    name='monoloco',
+    version=VERSION,
+    packages=[
+        'monoloco',
+        'monoloco.train',
+        'monoloco.predict',
+        'monoloco.eval',
+        'monoloco.prep',
+        'monoloco.visuals',
+        'monoloco.utils'
+    ],
+    license='GNU AGPLv3',
+    description='MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation',
+    long_description=open('README.md').read(),
+    long_description_content_type='text/markdown',
+    author='Lorenzo Bertoni',
+    author_email='lorenzo.bertoni@epfl.ch',
+    url='https://github.com/vita-epfl/monoloco',
+    zip_safe=False,
+
+    install_requires=[
+        'openpifpaf',
+        'nuscenes-devkit',  # for nuScenes dataset preprocessing
+        'tabulate',   # For evaluation
+        'pylint',
+        'pytest',
+    ],
+)