diff --git a/py/packages/genkit-anthropic/README.md b/py/packages/genkit-anthropic/README.md
index 43dd29bc49..ce947060af 100644
--- a/py/packages/genkit-anthropic/README.md
+++ b/py/packages/genkit-anthropic/README.md
@@ -5,7 +5,30 @@
 >
 > **Preview** — This plugin is in preview and may have API changes in future releases.
 
-This Genkit plugin provides a set of tools and utilities for working with Anthropic.
+Anthropic Claude model provider for Genkit.
+
+## Installation
+
+```bash
+uv add genkit-anthropic
+```
+
+## Usage
+
+```python
+from genkit import Genkit
+from genkit_anthropic import Anthropic
+
+ai = Genkit(plugins=[Anthropic()])
+
+res = await ai.generate(
+    model='anthropic/claude-sonnet-4-6',
+    prompt='Explain recursion in 10 words.',
+)
+print(res.text)
+```
+
+Set `ANTHROPIC_API_KEY` in the environment, or pass `api_key=` to `Anthropic()`.
 
 ## Disclaimer
 
diff --git a/py/packages/genkit-anthropic/pyproject.toml b/py/packages/genkit-anthropic/pyproject.toml
index a26174af15..b0f6a537a9 100644
--- a/py/packages/genkit-anthropic/pyproject.toml
+++ b/py/packages/genkit-anthropic/pyproject.toml
@@ -62,7 +62,6 @@ version = "0.9.0"
 
 [project.urls]
 "Bug Tracker"   = "https://github.com/genkit-ai/genkit/issues"
-Changelog       = "https://github.com/genkit-ai/genkit/blob/main/py/packages/genkit-anthropic/CHANGELOG.md"
 "Documentation" = "https://firebase.google.com/docs/genkit"
 "Homepage"      = "https://github.com/genkit-ai/genkit"
 "Repository"    = "https://github.com/genkit-ai/genkit/tree/main/py"
diff --git a/py/packages/genkit-django/README.md b/py/packages/genkit-django/README.md
index 1b0b668393..0e40e5b0c1 100644
--- a/py/packages/genkit-django/README.md
+++ b/py/packages/genkit-django/README.md
@@ -1,11 +1,11 @@
 # Genkit Django Plugin
 
-`genkit-plugin-django` exposes Genkit flows as HTTP endpoints in a Django application. It mirrors `genkit-plugin-flask` and `genkit-plugin-fastapi`: one decorator turns a `@ai.flow()` into a Django view that speaks the Genkit HTTP protocol (JSON envelope, optional SSE streaming, structured error responses).
+`genkit-django` exposes Genkit flows as HTTP endpoints in a Django application. It mirrors `genkit-flask` and `genkit-fastapi`: one decorator turns a `@ai.flow()` into a Django view that speaks the Genkit HTTP protocol (JSON envelope, optional SSE streaming, structured error responses).
 
 ## Install
 
 ```bash
-pip install genkit-plugin-django
+uv add genkit-django
 ```
 
 ## Usage
diff --git a/py/packages/genkit-django/pyproject.toml b/py/packages/genkit-django/pyproject.toml
index 4b06c640e5..7d6fb1d4c1 100644
--- a/py/packages/genkit-django/pyproject.toml
+++ b/py/packages/genkit-django/pyproject.toml
@@ -67,7 +67,6 @@ version = "0.9.0"
 
 [project.urls]
 "Bug Tracker"   = "https://github.com/genkit-ai/genkit/issues"
-Changelog       = "https://github.com/genkit-ai/genkit/blob/main/py/packages/genkit-django/CHANGELOG.md"
 "Documentation" = "https://firebase.google.com/docs/genkit"
 "Homepage"      = "https://github.com/genkit-ai/genkit"
 "Repository"    = "https://github.com/genkit-ai/genkit/tree/main/py"
diff --git a/py/packages/genkit-evaluators/README.md b/py/packages/genkit-evaluators/README.md
index d1970d1ec1..b928f9e5f2 100644
--- a/py/packages/genkit-evaluators/README.md
+++ b/py/packages/genkit-evaluators/README.md
@@ -11,30 +11,34 @@ No LLM or API keys required.
 ## Installation
 
 ```bash
-pip install genkit-plugin-evaluators
+uv add genkit-evaluators
 ```
 
 ## Usage
 
 ```python
 from genkit import Genkit
-from genkit_evaluators import GenkitEval
-
-ai = Genkit(plugins=[GenkitEval()])
-
-# Run evaluation with genkit eval-flow or programmatically
-evaluator = await ai.registry.resolve_evaluator('genkitEval/regex')
-result = await evaluator.run(
-    input={
-        'dataset': [
-            {'input': 'sample', 'output': 'banana', 'reference': 'ba?a?a'},
-            {'input': 'sample', 'output': 'apple', 'reference': 'ba?a?a'},
-        ],
-        'evalRunId': 'test',
-    }
+from genkit.evaluator import BaseDataPoint
+from genkit_evaluators import register_genkit_evaluators
+
+ai = Genkit()
+register_genkit_evaluators(ai)
+
+results = await ai.evaluate(
+    evaluator='genkitEval/regex',
+    dataset=[
+        BaseDataPoint(input='sample', output='banana', reference='ba?a?a'),
+        BaseDataPoint(input='sample', output='apple', reference='ba?a?a'),
+    ],
 )
 ```
 
+Or from the CLI:
+
+```bash
+genkit eval:run datasets/example.json --evaluators=genkitEval/regex
+```
+
 ## Evaluators
 
 - **genkitEval/regex** – Reference is a regex string. Output (stringified if needed) must match.
diff --git a/py/packages/genkit-evaluators/pyproject.toml b/py/packages/genkit-evaluators/pyproject.toml
index 5ea0274623..e3c35b742d 100644
--- a/py/packages/genkit-evaluators/pyproject.toml
+++ b/py/packages/genkit-evaluators/pyproject.toml
@@ -41,8 +41,10 @@ requires-python = ">=3.10"
 version = "0.9.0"
 
 [project.urls]
-"Homepage" = "https://github.com/genkit-ai/genkit"
-"Repository" = "https://github.com/genkit-ai/genkit/tree/main/py"
+"Bug Tracker"   = "https://github.com/genkit-ai/genkit/issues"
+"Documentation" = "https://firebase.google.com/docs/genkit"
+"Homepage"      = "https://github.com/genkit-ai/genkit"
+"Repository"    = "https://github.com/genkit-ai/genkit/tree/main/py"
 
 [build-system]
 build-backend = "hatchling.build"
diff --git a/py/packages/genkit-fastapi/README.md b/py/packages/genkit-fastapi/README.md
index 5ea483add0..3d6a875b42 100644
--- a/py/packages/genkit-fastapi/README.md
+++ b/py/packages/genkit-fastapi/README.md
@@ -1,34 +1,118 @@
 # Genkit FastAPI Plugin
 
-Serve Genkit flows as FastAPI endpoints.
+Expose Genkit flows and agents as HTTP endpoints in a FastAPI application.
 
 ## Installation
 
 ```bash
-pip install genkit-plugin-fastapi
+uv add genkit-fastapi genkit-google-genai
 ```
 
 ## Usage
 
+### Serving Flows (`serve_flow`)
+
+Use `serve_flow` to register a Genkit flow as a FastAPI endpoint:
+
+```python
 from fastapi import FastAPI
 from genkit import Genkit
-from genkit_fastapi import genkit_fastapi_handler
+from genkit_fastapi import serve_flow
 from genkit_google_genai import GoogleAI
 
-ai = Genkit(plugins=[GoogleAI()])
+ai = Genkit(plugins=[GoogleAI()], model='googleai/gemini-flash-latest')
 app = FastAPI()
 
 
+@ai.tool(description='Get current weather for a location')
+async def get_weather(location: str) -> str:
+    return f'Sunny in {location}'
+
+
 @ai.flow()
 async def chat_flow(prompt: str) -> str:
-    response = await ai.generate(prompt=prompt)
+    response = await ai.generate(
+        prompt=prompt,
+        tools=[get_weather],
+    )
     return response.text
 
 
-@app.post('/chat')
+# Mount flow endpoint at POST /api/chat_flow
+app.include_router(serve_flow(chat_flow), prefix='/api')
+```
+
+### Serving Agents (`serve_agent`)
+
+Use `serve_agent` to expose an agent as FastAPI routes (including `/getSnapshot` and `/abort` endpoints when session state storage is enabled):
+
+```python
+from fastapi import FastAPI
+from genkit import Genkit
+from genkit_fastapi import serve_agent
+from genkit_google_genai import GoogleAI
+
+ai = Genkit(plugins=[GoogleAI()], model='googleai/gemini-flash-latest')
+app = FastAPI()
+
+
+@ai.tool(description='Get current weather for a location')
+async def get_weather(location: str) -> str:
+    return f'Sunny in {location}'
+
+
+weather_agent = ai.define_agent(
+    name='weatherAgent',
+    model='googleai/gemini-flash-latest',
+    system='You are a helpful weather assistant.',
+    tools=[get_weather],
+)
+
+# Mount agent turn route at POST /api/weatherAgent (plus /getSnapshot and /abort companion endpoints)
+app.include_router(serve_agent(weather_agent), prefix='/api')
+```
+
+### Custom Base Path & Dependency Injection
+
+Customize the base path or resolve request context using FastAPI's dependency injection system:
+
+```python
+from fastapi import Depends, Header
+from genkit_fastapi import serve_flow
+
+
+async def user_context(authorization: str = Header(...)):
+    return {'uid': parse_token(authorization)}
+
+
+app.include_router(
+    serve_flow(
+        chat_flow,
+        base_path='/chat',
+        context_dependency=user_context,
+    ),
+    prefix='/api',
+)
+```
+
+### Decorator Handler (`genkit_fastapi_handler`)
+
+For custom route definitions, you can also use `@genkit_fastapi_handler`:
+
+```python
+from genkit_fastapi import genkit_fastapi_handler
+
+
+@app.post('/custom-chat', response_model=None)
 @genkit_fastapi_handler(ai)
-async def chat():
-    return chat_flow
+@ai.flow()
+async def custom_chat(prompt: str) -> str:
+    response = await ai.generate(
+        prompt=prompt,
+        tools=[get_weather],
+    )
+    return response.text
+```
 
 ## Running
 
@@ -42,10 +126,10 @@ uvicorn main:app
 
 ## Streaming
 
-The handler automatically supports streaming when the client sends `Accept: text/event-stream`:
+Endpoints automatically support streaming when the client sends `Accept: text/event-stream` or specifies `?stream=true`:
 
 ```bash
-curl -X POST http://localhost:8000/chat \
+curl -X POST http://localhost:8000/api/chat_flow \
   -H "Content-Type: application/json" \
   -H "Accept: text/event-stream" \
   -d '{"data": "Tell me a joke"}'
diff --git a/py/packages/genkit-fastapi/pyproject.toml b/py/packages/genkit-fastapi/pyproject.toml
index 0276b9ccc0..1fda37db25 100644
--- a/py/packages/genkit-fastapi/pyproject.toml
+++ b/py/packages/genkit-fastapi/pyproject.toml
@@ -56,7 +56,6 @@ version = "0.9.0"
 
 [project.urls]
 "Bug Tracker"   = "https://github.com/genkit-ai/genkit/issues"
-"Changelog"     = "https://github.com/genkit-ai/genkit/blob/main/py/packages/genkit-fastapi/CHANGELOG.md"
 "Documentation" = "https://firebase.google.com/docs/genkit"
 "Homepage"      = "https://github.com/genkit-ai/genkit"
 "Repository"    = "https://github.com/genkit-ai/genkit/tree/main/py"
diff --git a/py/packages/genkit-flask/README.md b/py/packages/genkit-flask/README.md
index 8e63b55eef..129934e8be 100644
--- a/py/packages/genkit-flask/README.md
+++ b/py/packages/genkit-flask/README.md
@@ -1,3 +1,31 @@
-# Genkit Flask plugin
+# Genkit Flask Plugin
 
-This Genkit plugin provides a set of tools and utilities for working with Flask.
+Expose Genkit flows as HTTP endpoints in a Flask application.
+
+## Installation
+
+```bash
+uv add genkit-flask genkit-google-genai
+```
+
+## Usage
+
+```python
+from flask import Flask
+from genkit import Genkit
+from genkit_flask import genkit_flask_handler
+from genkit_google_genai import GoogleAI
+
+app = Flask(__name__)
+ai = Genkit(plugins=[GoogleAI()], model='googleai/gemini-flash-latest')
+
+
+@app.post('/api/greet')
+@genkit_flask_handler(ai)
+@ai.flow()
+async def greet_user(name: str) -> str:
+    res = await ai.generate(prompt=f'Say hello to {name} in one sentence.')
+    return res.text
+```
+
+Requires Flask 3.1+.
diff --git a/py/packages/genkit-flask/pyproject.toml b/py/packages/genkit-flask/pyproject.toml
index 7412fed5f7..269be6e22c 100644
--- a/py/packages/genkit-flask/pyproject.toml
+++ b/py/packages/genkit-flask/pyproject.toml
@@ -48,7 +48,7 @@ dependencies = [
   "pydantic>=2.10.5",
   "flask>=3.1.3",
 ]
-description = "Genkit Firebase Plugin"
+description = "Genkit Flask Plugin"
 keywords = [
   "genkit",
   "ai",
@@ -68,7 +68,6 @@ version = "0.9.0"
 
 [project.urls]
 "Bug Tracker"   = "https://github.com/genkit-ai/genkit/issues"
-Changelog       = "https://github.com/genkit-ai/genkit/blob/main/py/packages/genkit-flask/CHANGELOG.md"
 "Documentation" = "https://firebase.google.com/docs/genkit"
 "Homepage"      = "https://github.com/genkit-ai/genkit"
 "Repository"    = "https://github.com/genkit-ai/genkit/tree/main/py"
diff --git a/py/packages/genkit-google-cloud/README.md b/py/packages/genkit-google-cloud/README.md
index 3e62320344..570a2c3593 100644
--- a/py/packages/genkit-google-cloud/README.md
+++ b/py/packages/genkit-google-cloud/README.md
@@ -1,4 +1,23 @@
-# Google Cloud Plugin
+# Genkit Google Cloud Plugin
 
-This Genkit plugin provides a set of tools and utilities for working with Google
-Cloud.
+Export Genkit telemetry to Google Cloud Trace, Cloud Monitoring, and Cloud Logging.
+
+## Installation
+
+```bash
+uv add genkit-google-cloud genkit-google-genai
+```
+
+## Usage
+
+```python
+from genkit import Genkit
+from genkit_google_cloud import enable_google_cloud_telemetry
+from genkit_google_genai import GoogleAI
+
+enable_google_cloud_telemetry(project_id='my-project')
+
+ai = Genkit(plugins=[GoogleAI()], model='googleai/gemini-flash-latest')
+```
+
+Requires Google Cloud Application Default Credentials (ADC) or explicit credentials.
diff --git a/py/packages/genkit-google-cloud/pyproject.toml b/py/packages/genkit-google-cloud/pyproject.toml
index e8a48aed7c..ffcfaa0721 100644
--- a/py/packages/genkit-google-cloud/pyproject.toml
+++ b/py/packages/genkit-google-cloud/pyproject.toml
@@ -70,7 +70,6 @@ version = "0.9.0"
 
 [project.urls]
 "Bug Tracker"   = "https://github.com/genkit-ai/genkit/issues"
-Changelog       = "https://github.com/genkit-ai/genkit/blob/main/py/packages/genkit-google-cloud/CHANGELOG.md"
 "Documentation" = "https://firebase.google.com/docs/genkit"
 "Homepage"      = "https://github.com/genkit-ai/genkit"
 "Repository"    = "https://github.com/genkit-ai/genkit/tree/main/py"
diff --git a/py/packages/genkit-google-genai/README.md b/py/packages/genkit-google-genai/README.md
index 16414ff408..b2668a04dd 100644
--- a/py/packages/genkit-google-genai/README.md
+++ b/py/packages/genkit-google-genai/README.md
@@ -5,9 +5,7 @@ This Genkit plugin provides a unified interface for Google AI (Gemini) and Verte
 ## Setup environment
 
 ```bash
-uv venv
-source .venv/bin/activate
-pip install genkit-plugins-google-genai
+uv add genkit genkit-google-genai
 ```
 
 ## Configuration
@@ -32,7 +30,7 @@ gcloud auth application-default login
 
 ### Dynamic Models
 
-The plugin automatically discovers available models from the API upon initialization. You can use any model name supported by the API (e.g., `googleai/gemini-2.0-flash-exp`, `vertexai/gemini-1.5-pro`).
+The plugin automatically discovers available models from the API upon initialization. You can use any model name supported by the API (e.g., `googleai/gemini-flash-latest`, `vertexai/gemini-2.5-pro`).
 
 ### Dynamic Configuration
 
@@ -47,40 +45,13 @@ config = GeminiConfigSchema.model_validate({
 })
 ```
 
-### Vertex AI Rerankers
-
-The VertexAI plugin provides semantic rerankers for improving RAG quality by re-scoring documents based on relevance:
-
-```python
-from genkit import Genkit
-from genkit_google_genai import VertexAI
-
-ai = Genkit(plugins=[VertexAI(project='my-project')])
-
-# Rerank documents after retrieval
-ranked_docs = await ai.rerank(
-    reranker='vertexai/semantic-ranker-default@latest',
-    query='What is machine learning?',
-    documents=retrieved_docs,
-    options={'top_n': 5},
-)
-```
-
-**Supported Models:**
-
-| Model | Description |
-|-------|-------------|
-| `semantic-ranker-default@latest` | Latest default semantic ranker |
-| `semantic-ranker-default-004` | Semantic ranker version 004 |
-| `semantic-ranker-fast-004` | Fast variant (lower latency) |
-
 ### Vertex AI Evaluators
 
 Built-in evaluators for assessing model output quality. Evaluators are automatically registered when using the VertexAI plugin and are accessed via `ai.evaluate()`:
 
 ```python
 from genkit import Genkit
-from genkit._core.typing import BaseDataPoint
+from genkit.evaluator import BaseDataPoint
 from genkit_google_genai import VertexAI
 
 ai = Genkit(plugins=[VertexAI(project='my-project')])
@@ -104,22 +75,22 @@ for result in results.root:
 ```
 
 
-**Supported Metrics:**
+**Supported evaluators:**
 
-| Metric | Description |
-|--------|-------------|
-| `BLEU` | Translation quality (compare to reference) |
-| `ROUGE` | Summarization quality |
-| `FLUENCY` | Language mastery and readability |
-| `SAFETY` | Harmful/inappropriate content detection |
-| `GROUNDEDNESS` | Hallucination detection |
-| `SUMMARIZATION_QUALITY` | Overall summarization ability |
+| Evaluator | Description |
+|-----------|-------------|
+| `vertexai/bleu` | Translation quality (compare to reference) |
+| `vertexai/rouge` | Summarization quality |
+| `vertexai/fluency` | Language mastery and readability |
+| `vertexai/safety` | Harmful/inappropriate content detection |
+| `vertexai/groundedness` | Hallucination detection |
+| `vertexai/summarization_quality` | Overall summarization ability |
 
 ## Examples
 
 For comprehensive usage examples, see:
 
-- [`py/samples/google-genai-media/README.md`](../../samples/google-genai-media/README.md) - Speech, image, and video generation
-- [`py/samples/gemini-code-execution/README.md`](../../samples/gemini-code-execution/README.md) - Gemini code execution
-- [`py/samples/gemini-context-caching/README.md`](../../samples/gemini-context-caching/README.md) - Context caching for large prompts
-- [`py/samples/vertexai-imagen/README.md`](../../samples/vertexai-imagen/README.md) - Vertex AI Imagen generation
+- [google-genai-media](https://github.com/genkit-ai/genkit/tree/main/py/samples/google-genai-media) - Speech, image, and video generation
+- [gemini-code-execution](https://github.com/genkit-ai/genkit/tree/main/py/samples/gemini-code-execution) - Gemini code execution
+- [gemini-context-caching](https://github.com/genkit-ai/genkit/tree/main/py/samples/gemini-context-caching) - Context caching for large prompts
+- [vertexai-imagen](https://github.com/genkit-ai/genkit/tree/main/py/samples/vertexai-imagen) - Vertex AI Imagen generation
diff --git a/py/packages/genkit-google-genai/pyproject.toml b/py/packages/genkit-google-genai/pyproject.toml
index 9e37ffdd84..d3274b8841 100644
--- a/py/packages/genkit-google-genai/pyproject.toml
+++ b/py/packages/genkit-google-genai/pyproject.toml
@@ -70,7 +70,6 @@ version = "0.9.0"
 
 [project.urls]
 "Bug Tracker"   = "https://github.com/genkit-ai/genkit/issues"
-Changelog       = "https://github.com/genkit-ai/genkit/blob/main/py/packages/genkit-google-genai/CHANGELOG.md"
 "Documentation" = "https://firebase.google.com/docs/genkit"
 "Homepage"      = "https://github.com/genkit-ai/genkit"
 "Repository"    = "https://github.com/genkit-ai/genkit/tree/main/py"
diff --git a/py/packages/genkit-middleware/README.md b/py/packages/genkit-middleware/README.md
index 353bac5b0f..610b61e772 100644
--- a/py/packages/genkit-middleware/README.md
+++ b/py/packages/genkit-middleware/README.md
@@ -1,6 +1,6 @@
 # Genkit Middleware Plugin
 
-A collection of middleware implementations for Firebase Genkit Python.
+A collection of middleware implementations for Genkit Python.
 
 ## Overview
 
@@ -19,9 +19,10 @@ Import the middleware classes you need and pass instances directly into `use=[]`
 
 ```python
 from genkit import Genkit
+from genkit_google_genai import GoogleAI
 from genkit_middleware import Retry, Fallback, Middleware
 
-ai = Genkit(plugins=[Middleware()])
+ai = Genkit(plugins=[GoogleAI(), Middleware()])
 
 response = await ai.generate(
     model='googleai/gemini-flash-latest',
@@ -38,7 +39,7 @@ These pre-packaged middlewares will be available to play with in the Dev UI by d
 ## Installation
 
 ```bash
-pip install genkit-plugin-middleware
+uv add genkit-middleware genkit-google-genai
 ```
 
 ## Usage
@@ -79,7 +80,7 @@ fallback = Fallback(
 )
 
 response = await ai.generate(
-    model='googleai/gemini-2.5-ultra',
+    model='googleai/gemini-pro-latest',
     prompt='Hello!',
     use=[fallback],
 )
@@ -90,17 +91,29 @@ response = await ai.generate(
 Requires approval before executing tools (useful for sensitive operations):
 
 ```python
+from pydantic import BaseModel, Field
+
 from genkit import restart_tool
 from genkit_middleware import ToolApproval
 
+
+class DeleteInput(BaseModel):
+    name: str = Field(description='Database name to delete')
+
+
+@ai.tool()
+async def delete_database(input: DeleteInput) -> str:
+    return f'Deleted {input.name}'
+
+
 approval = ToolApproval(
     allowed_tools=['get_weather', 'search'],  # These tools run without approval
 )
 
-response = await ai.generate(
+first = await ai.generate(
     model='googleai/gemini-flash-latest',
     prompt='Delete the database',
-    tools=[delete_database_tool],
+    tools=['delete_database'],
     use=[approval],
 )
 ```
@@ -109,18 +122,11 @@ When a non-allowed tool is called, execution is interrupted. Approve and re-run
 tool by restarting it with ``resumed_metadata`` that includes ``tool_approved``:
 
 ```python
-first = await ai.generate(
-    model='googleai/gemini-flash-latest',
-    prompt='Delete the database',
-    tools=[delete_database_tool],
-    use=[approval],
-)
-
 response = await ai.generate(
     model='googleai/gemini-flash-latest',
     prompt='Delete the database',
     messages=list(first.messages),
-    tools=[delete_database_tool],
+    tools=['delete_database'],
     use=[approval],
     resume_restart=restart_tool(
         interrupt=first.interrupts[0],
@@ -183,3 +189,29 @@ Provides four tools:
 - `read_file`: Read file content
 - `write_file`: Write to a file (requires `allow_write_access=True`)
 - `edit_file`: Edit file with string replacements (requires `allow_write_access=True`)
+
+### Artifacts
+
+Exposes `read_artifact` / `write_artifact` tools and lists session artifacts in the
+system prompt. Intended for agent sessions:
+
+```python
+from genkit_middleware import Artifacts, Middleware
+
+from genkit import Genkit
+from genkit.agent import InMemorySessionStore
+from genkit_google_genai import GoogleAI
+
+ai = Genkit(plugins=[GoogleAI(), Middleware()])
+
+agent = ai.define_agent(
+    name='workspaceAgent',
+    model='googleai/gemini-flash-latest',
+    use=[Artifacts()],
+    store=InMemorySessionStore(),
+)
+
+chat = agent.chat()
+await chat.send('Write poem.txt with a short poem about Python agents.')
+# chat.artifacts now includes poem.txt
+```
diff --git a/py/packages/genkit-ollama/README.md b/py/packages/genkit-ollama/README.md
index d63b55341c..b66e5c4290 100644
--- a/py/packages/genkit-ollama/README.md
+++ b/py/packages/genkit-ollama/README.md
@@ -49,8 +49,8 @@ print(len(embeddings[0].embedding))
 
 These snippets assume an async context (`await` inside an `async def`); pasting
 them at module top level raises `SyntaxError: 'await' outside function`. See the
-[runnable sample](../../samples/ollama-sample) for a complete `async def main()`
-plus `ai.run_main(...)` entry point.
+[runnable sample](https://github.com/genkit-ai/genkit/tree/main/py/samples/ollama-sample)
+for a complete `async def main()` plus `ai.run_main(...)` entry point.
 
 ### Streaming
 
@@ -168,7 +168,7 @@ with the URL it tried. Start the daemon (`ollama serve`) or set
 
 ## Sample
 
-See [`py/samples/ollama-sample`](../../samples/ollama-sample) for a runnable sample covering
+See [py/samples/ollama-sample](https://github.com/genkit-ai/genkit/tree/main/py/samples/ollama-sample) for a runnable sample covering
 chat, streaming, tool calling, and embeddings with a local Ollama server.
 
 ## Notes
diff --git a/py/packages/genkit-openai/README.md b/py/packages/genkit-openai/README.md
index acb21ebc16..34b6f6d5b3 100644
--- a/py/packages/genkit-openai/README.md
+++ b/py/packages/genkit-openai/README.md
@@ -1,8 +1,29 @@
-# OpenAI API Compatible model provider Plugin
+# Genkit OpenAI Plugin
 
-> **Community Plugin** — This plugin is community-maintained and is not an
-> official Google or OpenAI product. It is provided on an "as-is" basis.
->
 > **Preview** — This plugin is in preview and may have API changes in future releases.
 
-This Genkit plugin provides a set of tools and utilities for working with OpenAI.
+OpenAI-compatible model provider for Genkit (OpenAI, Azure OpenAI, and other
+compatible endpoints).
+
+## Installation
+
+```bash
+uv add genkit-openai
+```
+
+## Usage
+
+```python
+from genkit import Genkit
+from genkit_openai import OpenAI
+
+ai = Genkit(plugins=[OpenAI()])
+
+res = await ai.generate(
+    model='openai/gpt-5.2',
+    prompt='Suggest 2 catchy names for an AI newsletter.',
+)
+print(res.text)
+```
+
+Set `OPENAI_API_KEY` in the environment, or pass `api_key=` to `OpenAI()`.
diff --git a/py/packages/genkit-openai/pyproject.toml b/py/packages/genkit-openai/pyproject.toml
index 8c230cf526..34d28f5d7f 100644
--- a/py/packages/genkit-openai/pyproject.toml
+++ b/py/packages/genkit-openai/pyproject.toml
@@ -62,7 +62,6 @@ version = "0.9.0"
 
 [project.urls]
 "Bug Tracker"   = "https://github.com/genkit-ai/genkit/issues"
-Changelog       = "https://github.com/genkit-ai/genkit/blob/main/py/packages/genkit-openai/CHANGELOG.md"
 "Documentation" = "https://firebase.google.com/docs/genkit"
 "Homepage"      = "https://github.com/genkit-ai/genkit"
 "Repository"    = "https://github.com/genkit-ai/genkit/tree/main/py"
diff --git a/py/packages/genkit-vertexai/README.md b/py/packages/genkit-vertexai/README.md
index 36791583ea..7c43b6ffa4 100644
--- a/py/packages/genkit-vertexai/README.md
+++ b/py/packages/genkit-vertexai/README.md
@@ -1,4 +1,28 @@
-# Google Cloud Vertex AI Plugin
+# Genkit Vertex AI Plugin
 
-This Genkit plugin provides a set of tools and utilities for working with Google
-Cloud Vertex AI.
+Integrate Genkit with Google Cloud Vertex AI Model Garden.
+
+## Installation
+
+```bash
+uv add genkit-vertexai
+```
+
+## Usage
+
+```python
+from genkit import Genkit
+from genkit_vertexai.model_garden import ModelGarden
+
+ai = Genkit(
+    plugins=[ModelGarden(project_id='my-project', location='us-central1')],
+)
+
+res = await ai.generate(
+    model='modelgarden/anthropic/claude-3-5-sonnet-v2@20241022',
+    prompt='Explain recursion in 10 words.',
+)
+print(res.text)
+```
+
+Requires Google Cloud Application Default Credentials (ADC) or explicit credentials.
diff --git a/py/packages/genkit-vertexai/pyproject.toml b/py/packages/genkit-vertexai/pyproject.toml
index 3ad65e0f5b..920314402c 100644
--- a/py/packages/genkit-vertexai/pyproject.toml
+++ b/py/packages/genkit-vertexai/pyproject.toml
@@ -74,7 +74,6 @@ version = "0.9.0"
 
 [project.urls]
 "Bug Tracker"   = "https://github.com/genkit-ai/genkit/issues"
-Changelog       = "https://github.com/genkit-ai/genkit/blob/main/py/packages/genkit-vertexai/CHANGELOG.md"
 "Documentation" = "https://firebase.google.com/docs/genkit"
 "Homepage"      = "https://github.com/genkit-ai/genkit"
 "Repository"    = "https://github.com/genkit-ai/genkit/tree/main/py"
diff --git a/py/packages/genkit/README.md b/py/packages/genkit/README.md
index 5b0568dbf1..8f756cac29 100644
--- a/py/packages/genkit/README.md
+++ b/py/packages/genkit/README.md
@@ -11,8 +11,7 @@ you can use Genkit independently of any Google services.
 ## Setup Instructions
 
 ```bash
-pip install genkit
-pip install genkit-plugin-google-genai
+uv add genkit genkit-google-genai
 ```
 
 
@@ -23,7 +22,7 @@ from genkit_google_genai import GoogleAI
 
 ai = Genkit(
     plugins=[GoogleAI()],
-    model='googleai/gemini-2.0-flash',
+    model='googleai/gemini-flash-latest',
 )
 
 
diff --git a/py/packages/genkit/pyproject.toml b/py/packages/genkit/pyproject.toml
index 8f47919d3f..adf53fbefb 100644
--- a/py/packages/genkit/pyproject.toml
+++ b/py/packages/genkit/pyproject.toml
@@ -89,7 +89,6 @@ vertex-ai             = ["genkit-vertexai"]
 
 [project.urls]
 "Bug Tracker"   = "https://github.com/genkit-ai/genkit/issues"
-"Changelog"     = "https://github.com/genkit-ai/genkit/blob/main/py/packages/genkit/CHANGELOG.md"
 "Documentation" = "https://firebase.google.com/docs/genkit"
 "Homepage"      = "https://github.com/genkit-ai/genkit"
 "Repository"    = "https://github.com/genkit-ai/genkit/tree/main/py"