diff --git a/docs/design/package_structure_overview.dot b/docs/design/package_structure_overview.dot
index 6c5eba6345..9e6144708c 100644
--- a/docs/design/package_structure_overview.dot
+++ b/docs/design/package_structure_overview.dot
@@ -5,7 +5,7 @@ digraph {
 
   subgraph cluster_users {
     research [href="https://github.com/google-research/federated/blob/master" target="_parent", fillcolor="#E2F3EB", color="#57BB8A"]
-    examples [href="https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples" target="_parent", fillcolor="#E2F3EB", color="#57BB8A"]
+    examples [href="https://github.com/tensorflow/federated/blob/main/examples" target="_parent", fillcolor="#E2F3EB", color="#57BB8A"]
     tests [href="https://github.com/tensorflow/federated/blob/main/tensorflow_federated/python/tests" target="_parent", fillcolor="#E2F3EB", color="#57BB8A"]
   }
 
diff --git a/docs/program/federated_program.md b/docs/program/federated_program.md
index b8a9d6866e..7aa107f70d 100644
--- a/docs/program/federated_program.md
+++ b/docs/program/federated_program.md
@@ -7,7 +7,7 @@ especially its type system.
 For more information about federated program, see:
 
 *   [API Documentation](https://www.tensorflow.org/federated/api_docs/python/tff/program)
-*   [Examples](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/program)
+*   [Examples](https://github.com/tensorflow/federated/blob/main/examples/program)
 *   [Developer Guide](https://github.com/tensorflow/federated/blob/main/docs/program/guide.md)
 
 [TOC]
diff --git a/docs/program/guide.md b/docs/program/guide.md
index 6f0604fcd7..f50c10e07b 100644
--- a/docs/program/guide.md
+++ b/docs/program/guide.md
@@ -16,7 +16,7 @@ This section defines guidelines for how
 should be authored.
 
 See the example
-[program_logic.py](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/program/program_logic.py)
+[program_logic.py](https://github.com/tensorflow/federated/blob/main/examples/program/program_logic.py)
 for more information.
 
 ### Document Type Signatures
@@ -213,7 +213,7 @@ def program_logic(...) -> None:
 ### Tests
 
 **Do** provide unit tests for the program logic (e.g.
-[program_logic_test.py](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/program/program_logic_test.py)).
+[program_logic_test.py](https://github.com/tensorflow/federated/blob/main/examples/program/program_logic_test.py)).
 
 ## Program
 
@@ -222,14 +222,14 @@ This section defines guidelines for how a
 should be authored.
 
 See the example
-[program.py](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/program/program.py)
+[program.py](https://github.com/tensorflow/federated/blob/main/examples/program/program.py)
 for more information.
 
 ### Document the Program
 
 **Do** document the details of the program to the customer in the docstring of
 the module (e.g.
-[program.py](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/program/program.py)):
+[program.py](https://github.com/tensorflow/federated/blob/main/examples/program/program.py)):
 
 *   How to manually run the program.
 *   What platform, computations, and data sources are used in the program.
diff --git a/docs/tff_for_research.md b/docs/tff_for_research.md
index 2b0dffefec..f5b557b249 100644
--- a/docs/tff_for_research.md
+++ b/docs/tff_for_research.md
@@ -21,7 +21,7 @@ types of logic.
     encapsulate logic that runs in a single location (e.g., on clients or on a
     server). This code is typically written and tested without any `tff.*`
     references, and can be re-used outside of TFF. For example, the
-    [client training loop in Federated Averaging](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py#L184-L222)
+    [client training loop in Federated Averaging](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py#L184-L222)
     is implemented at this level.
 
 1.  TensorFlow Federated orchestration logic, which binds together the
@@ -29,12 +29,12 @@ types of logic.
     and then orchestrating them using abstractions like
     `tff.federated_broadcast` and `tff.federated_mean` inside a
     `tff.federated_computation`. See, for example, this
-    [orchestration for Federated Averaging](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tff.py#L112-L140).
+    [orchestration for Federated Averaging](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tff.py#L112-L140).
 
 1.  An outer driver script that simulates the control logic of a production FL
     system, selecting simulated clients from a dataset and then executing
     federated computations defined in 2. on those clients. For example,
-    [a Federated EMNIST experiment driver](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py).
+    [a Federated EMNIST experiment driver](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py).
 
 ## Federated learning datasets
 
@@ -114,17 +114,17 @@ TFF, depending on the desired level of customization.
 
 A minimal stand-alone implementation of the
 [Federated Averaging](https://arxiv.org/abs/1602.05629) algorithm is provided
-[here](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg).
+[here](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg).
 The code includes
-[TF functions](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py)
+[TF functions](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py)
 for local computation,
-[TFF computations](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tff.py)
+[TFF computations](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tff.py)
 for orchestration, and a
-[driver script](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py)
+[driver script](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py)
 on the EMNIST dataset as an example. These files can easily be adapted for
 customized applciations and algorithmic changes following detailed instructions
 in the
-[README](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/README.md).
+[README](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/README.md).
 
 A more general implementation of Federated Averaging can be found
 [here](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/python/learning/algorithms/fed_avg.py).
@@ -218,13 +218,13 @@ One approach is to let each client fine-tune a single global model (trained
 using federated learning) with their local data. This approach has connections
 to meta-learning, see, e.g., [this paper](https://arxiv.org/abs/1909.12488). An
 example of this approach is given in
-[`emnist_p13n_main.py`](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/personalization/emnist_p13n_main.py).
+[`emnist_p13n_main.py`](https://github.com/tensorflow/federated/blob/main/examples/personalization/emnist_p13n_main.py).
 To explore and compare different personalization strategies, you can:
 
 *   Define a personalization strategy by implementing a `tf.function` that
     starts from an initial model, trains and evaluates a personalized model
     using each client's local datasets. An example is given by
-    [`build_personalize_fn`](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/personalization/p13n_utils.py).
+    [`build_personalize_fn`](https://github.com/tensorflow/federated/blob/main/examples/personalization/p13n_utils.py).
 
 *   Define an `OrderedDict` that maps strategy names to the corresponding
     personalization strategies, and use it as the `personalize_fn_dict` argument
diff --git a/docs/tutorials/custom_federated_algorithm_with_tff_optimizers.ipynb b/docs/tutorials/custom_federated_algorithm_with_tff_optimizers.ipynb
index 910cf36e88..5f306fdd59 100644
--- a/docs/tutorials/custom_federated_algorithm_with_tff_optimizers.ipynb
+++ b/docs/tutorials/custom_federated_algorithm_with_tff_optimizers.ipynb
@@ -61,7 +61,7 @@
       "source": [
         "# Use TFF optimizers in custom iterative process\n",
         "\n",
-        "This is an alternative to the [Build Your Own Federated Learning Algorithm](building_your_own_federated_learning_algorithm.ipynb) tutorial and the [simple_fedavg](https://github.com/tensorflow/federated/tree/main/tensorflow_federated/examples/simple_fedavg) example to build a custom iterative process for the [federated averaging](https://arxiv.org/abs/1602.05629) algorithm. This tutorial will use [TFF optimizers](https://github.com/tensorflow/federated/tree/main/tensorflow_federated/python/learning/optimizers) instead of Keras optimizers.\n",
+        "This is an alternative to the [Build Your Own Federated Learning Algorithm](building_your_own_federated_learning_algorithm.ipynb) tutorial and the [simple_fedavg](https://github.com/tensorflow/federated/tree/main/examples/simple_fedavg) example to build a custom iterative process for the [federated averaging](https://arxiv.org/abs/1602.05629) algorithm. This tutorial will use [TFF optimizers](https://github.com/tensorflow/federated/tree/main/tensorflow_federated/python/learning/optimizers) instead of Keras optimizers.\n",
         "The TFF optimizer abstraction is desgined to be state-in-state-out to be easier to be incorporated in a TFF iterative process. The `tff.learning` APIs also accept TFF optimizers as input argument."
       ]
     },
@@ -124,7 +124,7 @@
       },
       "source": [
         "## Preparing data and model\n",
-        "The EMNIST data processing and model are very similar to the [simple_fedavg](https://github.com/tensorflow/federated/tree/main/tensorflow_federated/examples/simple_fedavg) example."
+        "The EMNIST data processing and model are very similar to the [simple_fedavg](https://github.com/tensorflow/federated/tree/main/examples/simple_fedavg) example."
       ]
     },
     {
diff --git a/docs/tutorials/random_noise_generation.ipynb b/docs/tutorials/random_noise_generation.ipynb
index e3f9ec5a6a..3244761306 100644
--- a/docs/tutorials/random_noise_generation.ipynb
+++ b/docs/tutorials/random_noise_generation.ipynb
@@ -575,7 +575,7 @@
         "id": "x9kc6G0RIATV"
       },
       "source": [
-        "Now let us use the helper class and `tf.random.stateless_normal` to generate (nested structure of) random noise in TFF. The following code snippet looks a lot like a TFF iterative process, see [simple_fedavg](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tff.py) as an example of expressing federated learning algorithm as TFF iterative process. The pseudo seed state here for random noise generation is `tf.Tensor` that can be easily transported in TFF and TF functions."
+        "Now let us use the helper class and `tf.random.stateless_normal` to generate (nested structure of) random noise in TFF. The following code snippet looks a lot like a TFF iterative process, see [simple_fedavg](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tff.py) as an example of expressing federated learning algorithm as TFF iterative process. The pseudo seed state here for random noise generation is `tf.Tensor` that can be easily transported in TFF and TF functions."
       ]
     },
     {
diff --git a/docs/tutorials/simulations_with_accelerators.ipynb b/docs/tutorials/simulations_with_accelerators.ipynb
index c0bc329ca5..1c6f9a2476 100644
--- a/docs/tutorials/simulations_with_accelerators.ipynb
+++ b/docs/tutorials/simulations_with_accelerators.ipynb
@@ -227,7 +227,7 @@
         "id": "QJZh5NoiG-hR"
       },
       "source": [
-        "We define a function preprocessing the EMNIST example following the [simple_fedavg](https://github.com/tensorflow/federated/tree/main/tensorflow_federated/examples/simple_fedavg) example. Note that the argument `client_epochs_per_round` controls the number of local epochs on clients in federated learning. "
+        "We define a function preprocessing the EMNIST example following the [simple_fedavg](https://github.com/tensorflow/federated/tree/main/examples/simple_fedavg) example. Note that the argument `client_epochs_per_round` controls the number of local epochs on clients in federated learning. "
       ]
     },
     {
@@ -342,7 +342,7 @@
         "id": "8OGBU1SLpyiR"
       },
       "source": [
-        "Now let us define the training loop for EMNIST. Note that `use_experimental_simulation_loop=True` in `tff.learning.algorithms.build_weighted_fed_avg` is suggested for performant TFF simulation, and required to take advantage of multi-GPUs on a single machine. See [simple_fedavg](https://github.com/tensorflow/federated/tree/main/tensorflow_federated/examples/simple_fedavg) example for how to define customized federated learning algorithm that has high performance on GPUs, one of the key features is to explicitly use `for ... iter(dataset)` for training loops. "
+        "Now let us define the training loop for EMNIST. Note that `use_experimental_simulation_loop=True` in `tff.learning.algorithms.build_weighted_fed_avg` is suggested for performant TFF simulation, and required to take advantage of multi-GPUs on a single machine. See [simple_fedavg](https://github.com/tensorflow/federated/tree/main/examples/simple_fedavg) example for how to define customized federated learning algorithm that has high performance on GPUs, one of the key features is to explicitly use `for ... iter(dataset)` for training loops. "
       ]
     },
     {
diff --git a/tensorflow_federated/examples/README.md b/examples/README.md
similarity index 100%
rename from tensorflow_federated/examples/README.md
rename to examples/README.md
diff --git a/tensorflow_federated/examples/custom_data_backend/BUILD b/examples/custom_data_backend/BUILD
similarity index 100%
rename from tensorflow_federated/examples/custom_data_backend/BUILD
rename to examples/custom_data_backend/BUILD
diff --git a/tensorflow_federated/examples/custom_data_backend/data_backend_example.cc b/examples/custom_data_backend/data_backend_example.cc
similarity index 100%
rename from tensorflow_federated/examples/custom_data_backend/data_backend_example.cc
rename to examples/custom_data_backend/data_backend_example.cc
diff --git a/tensorflow_federated/examples/custom_data_backend/data_backend_example.h b/examples/custom_data_backend/data_backend_example.h
similarity index 100%
rename from tensorflow_federated/examples/custom_data_backend/data_backend_example.h
rename to examples/custom_data_backend/data_backend_example.h
diff --git a/tensorflow_federated/examples/datasets/BUILD b/examples/datasets/BUILD
similarity index 100%
rename from tensorflow_federated/examples/datasets/BUILD
rename to examples/datasets/BUILD
diff --git a/tensorflow_federated/examples/datasets/load_flair.py b/examples/datasets/load_flair.py
similarity index 100%
rename from tensorflow_federated/examples/datasets/load_flair.py
rename to examples/datasets/load_flair.py
diff --git a/tensorflow_federated/examples/learning/federated_program/vizier/BUILD b/examples/learning/federated_program/vizier/BUILD
similarity index 100%
rename from tensorflow_federated/examples/learning/federated_program/vizier/BUILD
rename to examples/learning/federated_program/vizier/BUILD
diff --git a/tensorflow_federated/examples/learning/federated_program/vizier/data_sources.py b/examples/learning/federated_program/vizier/data_sources.py
similarity index 100%
rename from tensorflow_federated/examples/learning/federated_program/vizier/data_sources.py
rename to examples/learning/federated_program/vizier/data_sources.py
diff --git a/tensorflow_federated/examples/learning/federated_program/vizier/learning_process.py b/examples/learning/federated_program/vizier/learning_process.py
similarity index 100%
rename from tensorflow_federated/examples/learning/federated_program/vizier/learning_process.py
rename to examples/learning/federated_program/vizier/learning_process.py
diff --git a/tensorflow_federated/examples/learning/federated_program/vizier/program.py b/examples/learning/federated_program/vizier/program.py
similarity index 95%
rename from tensorflow_federated/examples/learning/federated_program/vizier/program.py
rename to examples/learning/federated_program/vizier/program.py
index 0a9c9c3f69..fd010db623 100644
--- a/tensorflow_federated/examples/learning/federated_program/vizier/program.py
+++ b/examples/learning/federated_program/vizier/program.py
@@ -36,9 +36,9 @@
 from vizier import pyvizier
 from vizier.client import client_abc
 
-from tensorflow_federated.examples.learning.federated_program.vizier import data_sources
-from tensorflow_federated.examples.learning.federated_program.vizier import learning_process
-from tensorflow_federated.examples.learning.federated_program.vizier import vizier_service
+from exampleslearning.federated_program.vizier import data_sources
+from exampleslearning.federated_program.vizier import learning_process
+from exampleslearning.federated_program.vizier import vizier_service
 
 
 _TOTAL_ROUNDS = 2
diff --git a/tensorflow_federated/examples/learning/federated_program/vizier/study_spec.textproto b/examples/learning/federated_program/vizier/study_spec.textproto
similarity index 100%
rename from tensorflow_federated/examples/learning/federated_program/vizier/study_spec.textproto
rename to examples/learning/federated_program/vizier/study_spec.textproto
diff --git a/tensorflow_federated/examples/learning/federated_program/vizier/vizier_service.py b/examples/learning/federated_program/vizier/vizier_service.py
similarity index 100%
rename from tensorflow_federated/examples/learning/federated_program/vizier/vizier_service.py
rename to examples/learning/federated_program/vizier/vizier_service.py
diff --git a/tensorflow_federated/examples/learning/federated_program/vizier/vizier_service_test.py b/examples/learning/federated_program/vizier/vizier_service_test.py
similarity index 94%
rename from tensorflow_federated/examples/learning/federated_program/vizier/vizier_service_test.py
rename to examples/learning/federated_program/vizier/vizier_service_test.py
index 9892726d20..a749ddcc41 100644
--- a/tensorflow_federated/examples/learning/federated_program/vizier/vizier_service_test.py
+++ b/examples/learning/federated_program/vizier/vizier_service_test.py
@@ -17,7 +17,7 @@
 
 from absl.testing import absltest
 
-from tensorflow_federated.examples.learning.federated_program.vizier import vizier_service
+from exampleslearning.federated_program.vizier import vizier_service
 
 from vizier.service import clients
 from vizier.service import pyvizier
diff --git a/tensorflow_federated/examples/personalization/BUILD b/examples/personalization/BUILD
similarity index 100%
rename from tensorflow_federated/examples/personalization/BUILD
rename to examples/personalization/BUILD
diff --git a/tensorflow_federated/examples/personalization/README.md b/examples/personalization/README.md
similarity index 92%
rename from tensorflow_federated/examples/personalization/README.md
rename to examples/personalization/README.md
index 6c4d7ef5b6..5353badef4 100644
--- a/tensorflow_federated/examples/personalization/README.md
+++ b/examples/personalization/README.md
@@ -39,7 +39,7 @@ an unbatched `tf.data.Dataset` for test, and an extra `context` object, trains a
 personalized model, and returns the evaluation metrics. Users can define
 whatever personalization strategies they like. An example of fine-tuning based
 personalization strategy is given by `build_personalize_fn` in
-[`p13n_utils`](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/personalization/p13n_utils.py).
+[`p13n_utils`](https://github.com/tensorflow/federated/blob/main/examples/personalization/p13n_utils.py).
 
 The
 [`tff.learning.build_personalization_eval_computation`](https://www.tensorflow.org/federated/api_docs/python/tff/learning/build_personalization_eval_computation)
@@ -49,7 +49,7 @@ time, starting from the same global model. Specifically, users define a
 and then pass it to the API as the `personalize_fn_dict` argument.
 
 In
-[our experiment](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/personalization/emnist_p13n_main.py),
+[our experiment](https://github.com/tensorflow/federated/blob/main/examples/personalization/emnist_p13n_main.py),
 we define and evaluate two fine-tuning based personalization strategies: one
 uses SGD and other other uses Adam optimizer.
 
@@ -60,7 +60,7 @@ The
 API has an argument `max_num_samples` with a default value 100. Metrics from at
 most `max_num_samples` clients (the clients are sampled without replacement)
 will be collected and returned. In
-[our experiment](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/personalization/emnist_p13n_main.py),
+[our experiment](https://github.com/tensorflow/federated/blob/main/examples/personalization/emnist_p13n_main.py),
 we set this value to be larger than the number of clients in the federated
 dataset, which means that metrics from all clients will be returned.
 
@@ -70,7 +70,7 @@ strategy names to the evaluation metrics of the corresponding personalization
 strategies. Each returned metric contains a list of scalars (each scalar comes
 from one sampled client). Metric values at the same position, e.g.,
 `metric_1[i]`, `metric_2[i]`, ..., corresponds to the same client. In
-[our experiment](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/personalization/emnist_p13n_main.py),
+[our experiment](https://github.com/tensorflow/federated/blob/main/examples/personalization/emnist_p13n_main.py),
 the baseline evaluation function is given by `evaluate_fn` in
-[`p13n_utils`](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/personalization/p13n_utils.py),
+[`p13n_utils`](https://github.com/tensorflow/federated/blob/main/examples/personalization/p13n_utils.py),
 which is the same evaluation function used by the personalization strategies.
diff --git a/tensorflow_federated/examples/personalization/emnist_p13n_main.py b/examples/personalization/emnist_p13n_main.py
similarity index 98%
rename from tensorflow_federated/examples/personalization/emnist_p13n_main.py
rename to examples/personalization/emnist_p13n_main.py
index 056d7e3cbd..116962b286 100644
--- a/tensorflow_federated/examples/personalization/emnist_p13n_main.py
+++ b/examples/personalization/emnist_p13n_main.py
@@ -21,8 +21,8 @@
 import tensorflow as tf
 import tensorflow_federated as tff
 
-from tensorflow_federated.examples.personalization.p13n_utils import build_personalize_fn
-from tensorflow_federated.examples.personalization.p13n_utils import evaluate_fn
+from examplespersonalization.p13n_utils import build_personalize_fn
+from examplespersonalization.p13n_utils import evaluate_fn
 
 
 def _get_emnist_datasets() -> (
diff --git a/tensorflow_federated/examples/personalization/p13n_utils.py b/examples/personalization/p13n_utils.py
similarity index 100%
rename from tensorflow_federated/examples/personalization/p13n_utils.py
rename to examples/personalization/p13n_utils.py
diff --git a/tensorflow_federated/examples/personalization/p13n_utils_test.py b/examples/personalization/p13n_utils_test.py
similarity index 97%
rename from tensorflow_federated/examples/personalization/p13n_utils_test.py
rename to examples/personalization/p13n_utils_test.py
index 06fecd9841..bbf3a48623 100644
--- a/tensorflow_federated/examples/personalization/p13n_utils_test.py
+++ b/examples/personalization/p13n_utils_test.py
@@ -18,7 +18,7 @@
 import tensorflow as tf
 import tensorflow_federated as tff
 
-from tensorflow_federated.examples.personalization import p13n_utils
+from examplespersonalization import p13n_utils
 
 _INPUT_DIM = 2
 _OUTPUT_DIM = 1
diff --git a/tensorflow_federated/examples/program/BUILD b/examples/program/BUILD
similarity index 100%
rename from tensorflow_federated/examples/program/BUILD
rename to examples/program/BUILD
diff --git a/tensorflow_federated/examples/program/computations.py b/examples/program/computations.py
similarity index 100%
rename from tensorflow_federated/examples/program/computations.py
rename to examples/program/computations.py
diff --git a/tensorflow_federated/examples/program/program.py b/examples/program/program.py
similarity index 97%
rename from tensorflow_federated/examples/program/program.py
rename to examples/program/program.py
index e4e81628fe..18986b839d 100644
--- a/tensorflow_federated/examples/program/program.py
+++ b/examples/program/program.py
@@ -55,8 +55,8 @@
 import tensorflow as tf
 import tensorflow_federated as tff
 
-from tensorflow_federated.examples.program import computations
-from tensorflow_federated.examples.program import program_logic
+from examplesprogram import computations
+from examplesprogram import program_logic
 
 _OUTPUT_DIR = flags.DEFINE_string('output_dir', None, 'The output path.')
 
diff --git a/tensorflow_federated/examples/program/program_logic.py b/examples/program/program_logic.py
similarity index 100%
rename from tensorflow_federated/examples/program/program_logic.py
rename to examples/program/program_logic.py
diff --git a/tensorflow_federated/examples/program/program_logic_test.py b/examples/program/program_logic_test.py
similarity index 99%
rename from tensorflow_federated/examples/program/program_logic_test.py
rename to examples/program/program_logic_test.py
index 89986ce325..2cffbb3fd8 100644
--- a/tensorflow_federated/examples/program/program_logic_test.py
+++ b/examples/program/program_logic_test.py
@@ -24,8 +24,8 @@
 import tensorflow as tf
 import tensorflow_federated as tff
 
-from tensorflow_federated.examples.program import computations
-from tensorflow_federated.examples.program import program_logic
+from examplesprogram import computations
+from examplesprogram import program_logic
 
 
 def _create_native_federated_context():
diff --git a/tensorflow_federated/examples/simple_fedavg/BUILD b/examples/simple_fedavg/BUILD
similarity index 100%
rename from tensorflow_federated/examples/simple_fedavg/BUILD
rename to examples/simple_fedavg/BUILD
diff --git a/tensorflow_federated/examples/simple_fedavg/README.md b/examples/simple_fedavg/README.md
similarity index 70%
rename from tensorflow_federated/examples/simple_fedavg/README.md
rename to examples/simple_fedavg/README.md
index 3b877544a4..ed7f760772 100644
--- a/tensorflow_federated/examples/simple_fedavg/README.md
+++ b/examples/simple_fedavg/README.md
@@ -11,9 +11,9 @@ for a more full-featured implementation.
 
 A minimal implementation of the
 [Federated Averaging](https://arxiv.org/abs/1602.05629) algorithm is provided
-[here](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg),
+[here](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg),
 along with an example
-[federated EMNIST experiment](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py).
+[federated EMNIST experiment](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py).
 The implementation demonstrates the three main types of logic of a typical
 federated learning simulation.
 
@@ -32,59 +32,59 @@ federated learning simulation.
 This EMNIST example can easily be adapted for experimental changes:
 
 *   In the driver file
-    [emnist_fedavg_main](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py),
+    [emnist_fedavg_main](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py),
     we can change the
-    [dataset](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py#L49-L79),
+    [dataset](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py#L49-L79),
     the
-    [neural network architecture](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py#L82-L122),
+    [neural network architecture](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py#L82-L122),
     the
-    [server_optimizer](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py#L125-L126),
+    [server_optimizer](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py#L125-L126),
     and the
-    [client_optimizer](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py#L129-L130)
+    [client_optimizer](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py#L129-L130)
     for cutomized applications. Note that we need a
-    [model wrapper](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py#L151-152),
+    [model wrapper](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py#L151-152),
     and build an
-    [iterative process](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py#L154-L155)
+    [iterative process](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py#L154-L155)
     with TFF. We define a stand-alone model wrapper for keras models in
-    [simple_fedavg_tf](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py#L39-L81),
+    [simple_fedavg_tf](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py#L39-L81),
     which can be substituted with `tff.learning.models.VariableModel` by calling
     `tff.learning.models.from_keras_model`. Note that the inner
-    [keras_model](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py#L174)
+    [keras_model](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py#L174)
     of `tff.learning.models.VariableModel` may not be directly accessible for
     evaluation.
 
 *   In the TF function file
-    [simple_fedavg_tf](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py),
+    [simple_fedavg_tf](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py),
     we have more control over the local computations performed in optimization
     process. In each round, on the server side, we will update the
-    [ServerState](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py#L102-L113)
+    [ServerState](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py#L102-L113)
     in
-    [server_update](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py#L131-L141)
+    [server_update](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py#L131-L141)
     function; we then build a
-    [BroadcastMessage](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py#L116-L128)
+    [BroadcastMessage](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py#L116-L128)
     with the
-    [build_server_broadcast_message](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py#L165-L181)
+    [build_server_broadcast_message](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py#L165-L181)
     function to prepare for broadcasting from server to clients; on the client
     side, we perform local updates with the
-    [client_update](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py#L184-L222)
+    [client_update](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py#L184-L222)
     function and return
-    [ClientOutput](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py#L84-L99)
+    [ClientOutput](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py#L84-L99)
     to be sent back to server. Note that server_optimizer defined in
-    [emnist_fedavg_main](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py#L125-L126)
+    [emnist_fedavg_main](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py#L125-L126)
     is used in
-    [server_update](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py#L131-L141)
+    [server_update](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py#L131-L141)
     function; client_optimizer defined in
-    [emnist_fedavg_main](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py#L129-L130)
+    [emnist_fedavg_main](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py#L129-L130)
     is used in
-    [client_update](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py#L184-L222).
+    [client_update](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py#L184-L222).
     These functions are used as local computation building blocks in the overall
     TFF computation, which handles the broadcasting and aggregation between
     server and clients.
 
 *   In the TFF file
-    [simple_fedavg_tff](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tff.py),
+    [simple_fedavg_tff](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tff.py),
     we have control over the orchestration strategy. We take the
-    [weighted average](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tff.py#L132-L133)
+    [weighted average](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tff.py#L132-L133)
     of client updates to update the model kept in server state. More detailed
     instruction on the usage of TFF functions `federated_broadcast`,
     `federated_map`, and `federated_mean` can be found in the
@@ -92,33 +92,33 @@ This EMNIST example can easily be adapted for experimental changes:
 
 We expect researchers working on applications and models only need to change the
 driver file
-[emnist_fedavg_main](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py),
+[emnist_fedavg_main](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py),
 researchers working on optimization may implement most of the ideas by writing
 pure TF code in the TF file
-[simple_fedavg_tf](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py),
+[simple_fedavg_tf](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py),
 while researchers who need more control over the orchestration strategy may get
 familiar with TFF code in
-[simple_fedavg_tff](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tff.py).
+[simple_fedavg_tff](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tff.py).
 We encourage readers to consider the following exercises for using this set of
 code for your research:
 
 1.  Try a more complicated server optimizer such as ADAM. You only need to
     change
-    [emnist_fedavg_main](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py).
+    [emnist_fedavg_main](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py).
 
 1.  Implement a model that uses L2 regularization. You will need to change the
     model definition in
-    [emnist_fedavg_main](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py)
+    [emnist_fedavg_main](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/emnist_fedavg_main.py)
     and add Keras regularization losses in the `KerasModelWrapper` class in
-    [simple_fedavg_tf](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py).
+    [simple_fedavg_tf](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py).
 
 1.  Implement a decaying learning rate schedule on the clients based on the
     global round, using the `round_num` broadcasted to the clients in
-    [simple_fedavg_tf](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py).
+    [simple_fedavg_tf](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tf.py).
 
 1.  Implement a more complicated aggregation procedure that drops the client
     updates with the largest and smallest l2 norms. You will need to change
-    [simple_fedavg_tff](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tff.py).
+    [simple_fedavg_tff](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg/simple_fedavg_tff.py).
 
 ## Citation
 
diff --git a/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py b/examples/simple_fedavg/emnist_fedavg_main.py
similarity index 98%
rename from tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py
rename to examples/simple_fedavg/emnist_fedavg_main.py
index e1562cc607..bc07e9b7d4 100644
--- a/tensorflow_federated/examples/simple_fedavg/emnist_fedavg_main.py
+++ b/examples/simple_fedavg/emnist_fedavg_main.py
@@ -27,7 +27,7 @@
 import tensorflow as tf
 import tensorflow_federated as tff
 
-from tensorflow_federated.examples.simple_fedavg import simple_fedavg_tff
+from examplessimple_fedavg import simple_fedavg_tff
 
 # Training hyperparameters
 flags.DEFINE_integer('total_rounds', 256, 'Number of total training rounds.')
diff --git a/tensorflow_federated/examples/simple_fedavg/simple_fedavg_test.py b/examples/simple_fedavg/simple_fedavg_test.py
similarity index 99%
rename from tensorflow_federated/examples/simple_fedavg/simple_fedavg_test.py
rename to examples/simple_fedavg/simple_fedavg_test.py
index a2fadbb6bb..120ef99c1e 100644
--- a/tensorflow_federated/examples/simple_fedavg/simple_fedavg_test.py
+++ b/examples/simple_fedavg/simple_fedavg_test.py
@@ -23,8 +23,8 @@
 import tensorflow as tf
 import tensorflow_federated as tff
 
-from tensorflow_federated.examples.simple_fedavg import simple_fedavg_tf
-from tensorflow_federated.examples.simple_fedavg import simple_fedavg_tff
+from examplessimple_fedavg import simple_fedavg_tf
+from examplessimple_fedavg import simple_fedavg_tff
 
 
 def _create_test_cnn_model():
diff --git a/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py b/examples/simple_fedavg/simple_fedavg_tf.py
similarity index 100%
rename from tensorflow_federated/examples/simple_fedavg/simple_fedavg_tf.py
rename to examples/simple_fedavg/simple_fedavg_tf.py
diff --git a/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tff.py b/examples/simple_fedavg/simple_fedavg_tff.py
similarity index 93%
rename from tensorflow_federated/examples/simple_fedavg/simple_fedavg_tff.py
rename to examples/simple_fedavg/simple_fedavg_tff.py
index ac9f3094b1..155a6ecff6 100644
--- a/tensorflow_federated/examples/simple_fedavg/simple_fedavg_tff.py
+++ b/examples/simple_fedavg/simple_fedavg_tff.py
@@ -29,12 +29,12 @@
 import tensorflow as tf
 import tensorflow_federated as tff
 
-from tensorflow_federated.examples.simple_fedavg.simple_fedavg_tf import batch_client_update
-from tensorflow_federated.examples.simple_fedavg.simple_fedavg_tf import build_server_broadcast_message
-from tensorflow_federated.examples.simple_fedavg.simple_fedavg_tf import client_update
-from tensorflow_federated.examples.simple_fedavg.simple_fedavg_tf import init_client_ouput
-from tensorflow_federated.examples.simple_fedavg.simple_fedavg_tf import server_update
-from tensorflow_federated.examples.simple_fedavg.simple_fedavg_tf import ServerState
+from examplessimple_fedavg.simple_fedavg_tf import batch_client_update
+from examplessimple_fedavg.simple_fedavg_tf import build_server_broadcast_message
+from examplessimple_fedavg.simple_fedavg_tf import client_update
+from examplessimple_fedavg.simple_fedavg_tf import init_client_ouput
+from examplessimple_fedavg.simple_fedavg_tf import server_update
+from examplessimple_fedavg.simple_fedavg_tf import ServerState
 
 
 def _initialize_optimizer_vars(
diff --git a/tensorflow_federated/examples/stateful_clients/BUILD b/examples/stateful_clients/BUILD
similarity index 100%
rename from tensorflow_federated/examples/stateful_clients/BUILD
rename to examples/stateful_clients/BUILD
diff --git a/tensorflow_federated/examples/stateful_clients/README.md b/examples/stateful_clients/README.md
similarity index 96%
rename from tensorflow_federated/examples/stateful_clients/README.md
rename to examples/stateful_clients/README.md
index bb8526c71f..a01045252e 100644
--- a/tensorflow_federated/examples/stateful_clients/README.md
+++ b/examples/stateful_clients/README.md
@@ -9,7 +9,7 @@ protection.
 
 This project is based on the standalone implementaion of Federated Averaging
 algorithm in
-[`simple_fedavg`](https://github.com/tensorflow/federated/blob/main/tensorflow_federated/examples/simple_fedavg).
+[`simple_fedavg`](https://github.com/tensorflow/federated/blob/main/examples/simple_fedavg).
 We introduce a coutner on each client, which tracks the total number of
 iterations for model training on the clients. For example, if client A has been
 sampled m times at round n, and each time local model training has been run with
diff --git a/tensorflow_federated/examples/stateful_clients/emnist_fedavg_main.py b/examples/stateful_clients/emnist_fedavg_main.py
similarity index 97%
rename from tensorflow_federated/examples/stateful_clients/emnist_fedavg_main.py
rename to examples/stateful_clients/emnist_fedavg_main.py
index 8851806015..a8b204ba7a 100644
--- a/tensorflow_federated/examples/stateful_clients/emnist_fedavg_main.py
+++ b/examples/stateful_clients/emnist_fedavg_main.py
@@ -25,8 +25,8 @@
 import tensorflow as tf
 import tensorflow_federated as tff
 
-from tensorflow_federated.examples.stateful_clients import stateful_fedavg_tf
-from tensorflow_federated.examples.stateful_clients import stateful_fedavg_tff
+from examplesstateful_clients import stateful_fedavg_tf
+from examplesstateful_clients import stateful_fedavg_tff
 
 # Training hyperparameters
 flags.DEFINE_integer('total_rounds', 256, 'Number of total training rounds.')
diff --git a/tensorflow_federated/examples/stateful_clients/stateful_fedavg_test.py b/examples/stateful_clients/stateful_fedavg_test.py
similarity index 98%
rename from tensorflow_federated/examples/stateful_clients/stateful_fedavg_test.py
rename to examples/stateful_clients/stateful_fedavg_test.py
index a5050955f3..c26039a07e 100644
--- a/tensorflow_federated/examples/stateful_clients/stateful_fedavg_test.py
+++ b/examples/stateful_clients/stateful_fedavg_test.py
@@ -22,8 +22,8 @@
 import tensorflow as tf
 import tensorflow_federated as tff
 
-from tensorflow_federated.examples.stateful_clients import stateful_fedavg_tf
-from tensorflow_federated.examples.stateful_clients import stateful_fedavg_tff
+from examplesstateful_clients import stateful_fedavg_tf
+from examplesstateful_clients import stateful_fedavg_tff
 
 
 def _create_test_cnn_model():
diff --git a/tensorflow_federated/examples/stateful_clients/stateful_fedavg_tf.py b/examples/stateful_clients/stateful_fedavg_tf.py
similarity index 100%
rename from tensorflow_federated/examples/stateful_clients/stateful_fedavg_tf.py
rename to examples/stateful_clients/stateful_fedavg_tf.py
diff --git a/tensorflow_federated/examples/stateful_clients/stateful_fedavg_tff.py b/examples/stateful_clients/stateful_fedavg_tff.py
similarity index 98%
rename from tensorflow_federated/examples/stateful_clients/stateful_fedavg_tff.py
rename to examples/stateful_clients/stateful_fedavg_tff.py
index 2db8323521..626867eff1 100644
--- a/tensorflow_federated/examples/stateful_clients/stateful_fedavg_tff.py
+++ b/examples/stateful_clients/stateful_fedavg_tff.py
@@ -30,7 +30,7 @@
 import tensorflow as tf
 import tensorflow_federated as tff
 
-from tensorflow_federated.examples.stateful_clients import stateful_fedavg_tf
+from examplesstateful_clients import stateful_fedavg_tf
 
 
 def _initialize_optimizer_vars(model, optimizer):