google · koverholt · Jul 24, 2026
diff --git a/docs/agents/config.md b/docs/agents/config.md
@@ -302,9 +302,8 @@ limitations:
 
 ## Next steps
 
-For ideas on how and what to build with ADK Agent Configs, see the yaml-based
-agent definitions in the ADK
-[adk-samples](https://github.com/search?q=repo:google/adk-python+path:/%5Econtributing%5C/samples%5C//+root_agent.yaml&type=code)
-repository. For detailed information on the syntax and settings supported by
+For ideas on what to build, see the
+[sample agent configs](https://github.com/search?q=repo:google/adk-python+path:/%5Econtributing%5C/samples%5C//+root_agent.yaml&type=code)
+in the `adk-python` repository. For detailed information on the syntax and settings supported by
 the Agent Config format, see the
 [Agent Config syntax reference](/api-reference/agentconfig/).
diff --git a/docs/agents/models/google-gemma.md b/docs/agents/models/google-gemma.md
@@ -236,7 +236,6 @@ food_tour_app/
 ├── __init__.py
 └── agent.py
 ```
-**Full project can be found [here](https://github.com/google/adk-samples/tree/main/python/agents/gemma-food-tour-guide)**
 
 `agent.py`
 ```python

diff --git a/docs/evaluate/user-sim.md b/docs/evaluate/user-sim.md
@@ -47,13 +47,6 @@ You can also specify a pre-built `user_persona` in the following manner:
 
 While the conversation plan dictates what must be accomplished, the persona dictates how the model phrases its queries and reacts to the agent's responses.
 
-!!! tip "Try it in Colab"
-
-    Test this entire workflow yourself in an interactive notebook on
-    [Simulating User Conversations to Dynamically Evaluate ADK Agents](https://github.com/google/adk-samples/blob/main/python/notebooks/evaluation/user_simulation_in_adk_evals.ipynb).
-    You'll define a conversation scenario, run a "dry run" to check the
-    dialogue, and then perform a full evaluation to score the agent's responses.
-
 ## User personas
 
 <div class="language-support-tag">

diff --git a/docs/grounding/index.md b/docs/grounding/index.md
@@ -34,14 +34,6 @@ ADK supports multiple grounding approaches:
 
     - [Blog post: 10-minute Agentic RAG with Vector Search 2.0 and ADK](https://medium.com/google-cloud/10-minute-agentic-rag-with-the-new-vector-search-2-0-and-adk-655fff0bacac)
 
--   :material-notebook: **Vector Search 2.0 Travel Agent Notebook**
-
-    ---
-
-    A hands-on Jupyter notebook companion to the Agentic RAG blog post. Build an end-to-end travel agent using real Airbnb data, auto-embeddings, hybrid search with RRF ranking, and ADK tool integration.
-
-    - [Vector Search 2.0 Travel Agent Notebook](https://github.com/google/adk-samples/blob/main/python/notebooks/grounding/vectorsearch2_travel_agent.ipynb)
-
 -   :material-text-search: **Deep Search Agent**
 
     ---
@@ -50,12 +42,4 @@ ADK supports multiple grounding approaches:
 
     - [Deep Search Agent](https://github.com/google/adk-samples/tree/main/python/agents/deep-search)
 
--   :material-file-document-multiple: **RAG Agent**
-
-    ---
-
-    A document Q&A agent powered by Knowledge Engine. Upload documents and ask questions to receive accurate answers with citations formatted as URLs pointing to source materials.
-
-    - [RAG Agent](https://github.com/google/adk-samples/tree/main/python/agents/RAG)
-
 </div>
diff --git a/docs/integrations/knowledge-engine.md b/docs/integrations/knowledge-engine.md
@@ -15,9 +15,7 @@ The `vertex_ai_rag_retrieval` tool allows the agent to perform private data
 retrieval using Knowledge Engine.
 
 When you use grounding with Knowledge Engine, you need to prepare a RAG corpus
-beforehand. Please refer to the [RAG ADK agent
-sample](https://github.com/google/adk-samples/blob/main/python/agents/RAG/rag/shared_libraries/prepare_corpus_and_data.py)
-or [Knowledge Engine
+beforehand. Please refer to the [Knowledge Engine
 page](https://cloud.google.com/vertex-ai/generative-ai/docs/rag-engine/rag-quickstart)
 for setting it up.
 

diff --git a/docs/streaming/dev-guide/part1.md b/docs/streaming/dev-guide/part1.md
@@ -6,9 +6,7 @@ Google's Agent Development Kit ([ADK](https://adk.dev)) provides a production-re
 
 ## ADK Gemini Live API Toolkit Demo
 
-To help you understand the concepts in this guide, we provide a working demo application that showcases ADK bidirectional streaming in action. This FastAPI-based demo implements the complete streaming lifecycle with a practical, real-world architecture.
-
-**Demo Repository**: [adk-samples/python/agents/bidi-demo](https://github.com/google/adk-samples/tree/main/python/agents/bidi-demo)
+To help you understand the concepts in this guide, we reference a demo application that showcases ADK bidirectional streaming in action. This FastAPI-based demo implements the complete streaming lifecycle with a practical, real-world architecture.
 
 ![ADK Gemini Live API Toolkit Demo](assets/bidi-demo-screen.png)
 
@@ -20,9 +18,7 @@ The demo features:
 - **Interactive UI**: Web interface with event console for monitoring Live API events
 - **Google Search Integration**: Agent equipped with tool calling capabilities
 
-**We strongly recommend installing and running this demo** before diving into the guide. Hands-on experimentation will help you understand the concepts more deeply, and the demo code serves as a practical reference throughout all parts of this guide.
-
-For installation instructions and usage details, see the [demo README](https://github.com/google/adk-samples/tree/main/python/agents/bidi-demo).
+The demo code serves as a practical reference throughout all parts of this guide, with code snippets linked inline as each concept is introduced.
 
 ## 1.1 What is Bidi-streaming?
 

diff --git a/docs/streaming/index.md b/docs/streaming/index.md
@@ -41,17 +41,6 @@ text, audio, and video inputs, and they can provide text and audio output.
     - [LensMosaic Demo](https://lens-mosaic-nhhfh7g7iq-uc.a.run.app)
     - [Source Code](https://github.com/kazunori279/lens-mosaic)
 
--   :material-microphone-outline: **ADK Gemini Live API Toolkit Demo**
-
-    ---
-
-    [![Bidi Demo screenshot](https://raw.githubusercontent.com/google/adk-samples/main/python/agents/bidi-demo/assets/bidi-demo-screen.png)](https://bidi-demo-761793285222.us-central1.run.app/)
-
-    A production-ready reference implementation showcasing ADK Gemini Live API Toolkit with multimodal support (text, audio, image). This FastAPI-based demo demonstrates real-time WebSocket communication, automatic transcription, tool calling with Google Search, and complete streaming lifecycle management.
-
-    - [Bidi Demo](https://bidi-demo-761793285222.us-central1.run.app/)
-    - [Source Code](https://github.com/google/adk-samples/tree/main/python/agents/bidi-demo)
-
 </div>
 
 <div class="grid cards" markdown>
@@ -65,14 +54,6 @@ text, audio, and video inputs, and they can provide text and audio output.
 
     - [Quickstart (Gemini Live API Toolkit)](../get-started/streaming/quickstart-streaming.md)
 
--   :material-console-line: **Gemini Live API Toolkit Demo Application**
-
-    ---
-
-    A production-ready reference implementation showcasing ADK Gemini Live API Toolkit with multimodal support (text, audio, image). This FastAPI-based demo demonstrates real-time WebSocket communication, automatic transcription, tool calling with Google Search, and complete streaming lifecycle management. This demo is extensively referenced throughout the development guide series.
-
-    - [ADK Gemini Live API Toolkit Demo](https://github.com/google/adk-samples/tree/main/python/agents/bidi-demo)
-
 -   :material-console-line: **Blog post: ADK Gemini Live API Toolkit Visual Guide**
 
     ---

diff --git a/lychee.toml b/lychee.toml
@@ -24,5 +24,4 @@ host_request_interval = "1s"
 # Add paths here for directories containing partial/template files
 exclude_path = [
     "_includes",
-    "adk-samples",  # TODO: Remove at release time
 ]