Google Adk Python
- 378 installs
- 124 repo stars
- Updated February 6, 2026
- cnemri/google-genai-skills
google-adk-python is an agent skill that helps implement Python AI agents with Google ADK including tool registration, session handling, multi-turn orchestration, and GenAI model configuration for developers building pro
About
google-adk-python is a skill in cnemri/google-genai-skills for implementing Python agents on Google's Agent Development Kit. The skill walks developers through registering tools, managing sessions, orchestrating multi-turn conversations, and configuring GenAI models within ADK patterns. Teams reach for google-adk-python when scaffolding agent services that must integrate Google's GenAI stack instead of ad-hoc LangChain glue. Expect guidance on ADK project structure, tool hooks, and session lifecycle suitable for Claude Code-assisted implementation of backend agent runners.
- Google ADK
- Python agent runtime
- tool definitions
- GenAI SDK
- multi-turn sessions
Google Adk Python by the numbers
- 378 all-time installs (skills.sh)
- Ranked #2,058 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Jul 29, 2026 (Skillselion catalog sync)
npx skills add https://github.com/cnemri/google-genai-skills --skill google-adk-pythonAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 378 |
|---|---|
| repo stars | ★ 124 |
| Last updated | February 6, 2026 |
| Repository | cnemri/google-genai-skills ↗ |
How do you build Python agents with Google ADK?
Implement Python AI agents with Google ADK including tool registration, session handling, multi-turn orchestration, and GenAI model configuration.
Who is it for?
Python developers adopting Google ADK who need agent scaffolding with tools, sessions, and multi-turn GenAI orchestration in Claude-assisted workflows.
Skip if: JavaScript-only stacks or teams not using Google's Agent Development Kit who do not need GenAI agent backends.
When should I use this skill?
User implements Python agents with Google ADK, tool registration, session handling, or GenAI model configuration
What you get
ADK agent modules with registered tools, session handlers, and configured GenAI model orchestration code
- ADK agent module
- Tool registration code
- Session orchestration setup
Files
Google ADK (Python) Skill
This skill provides comprehensive documentation and Python examples for the Google Agent Development Kit (ADK). It maps documentation topics to their corresponding Python code snippets.
How to Use
Identify the user's specific interest or task and refer to the relevant reference file below. Each reference file contains links to the official documentation (Markdown) and the corresponding Python examples (raw code).
Topics
1. Getting Started
For installation, quickstarts, and basic agent setup.
- Reference: references/get-started.md
2. Agents & Models
For creating different types of agents (LLM, Workflow, Loop, Parallel, Sequential) and configuring specific models (Gemini, Anthropic, etc.).
- Agents Reference: references/agents.md
- Models Reference: references/models.md
3. Tools (Basic & Advanced)
For integrating tools like Google Search, Code Execution, BigQuery, third-party services (GitHub, Jira, etc.), MCP, and Grounding.
- Basic Tools Reference: references/tools.md
- Advanced Tools Reference: references/advanced-tools.md
4. Streaming
For building real-time, low-latency streaming agents (audio/video).
- Reference: references/streaming.md
5. Callbacks
For hooking into agent lifecycle events (before/after agent, model, tool execution).
- Reference: references/callbacks.md
6. Runtime & Architecture
For deep dives into the Runtime, Sessions, Memory, Context, Events, Artifacts, and Plugins.
- Reference: references/runtime-arch.md
7. Deployment & Operations
For deploying agents (Cloud Run, GKE) and observability (Logging, Tracing, Evaluation).
- Reference: references/deploy-ops.md
8. Tutorials & Samples
For end-to-end tutorials and complete agent samples (e.g., YouTube Shorts Assistant, Weather Agent).
- Reference: references/tutorials.md
9. API Reference
For REST API details.
- Reference: references/api.md
10. General Information
For project info, community, release notes, and limitations.
- Reference: references/general.md
Instructions
- When a user asks about a specific topic, load the corresponding reference file to get the URLs for the documentation and code.
- You can read the content of the linked files using
web_fetchorrun_shell_commandwithcurlif you need to provide the actual content to the user. - Always prefer providing the Python example code when explaining a concept.
Advanced Tools & Integrations
Model Context Protocol (MCP)
Grounding
Visual Builder
Third-Party Tools
- Overview
- AG UI
- Asana
- Atlassian
- Cartesia
- Chroma
- Daytona
- ElevenLabs
- GitHub
- GitLab
- Hugging Face
- Linear
- MongoDB
- n8n
- Notion
- PayPal
- Postman
- Qdrant
- Stripe
Additional Google Cloud Tools
- Apigee API Hub
- Application Integration
- Bigtable
- Spanner
- Pub/Sub
- Vertex AI RAG Engine
- MCP Toolbox for Databases
Advanced Configurations
Python Examples
- Bigtable: bigtable.py
- Pub/Sub: pubsub.py
- Spanner: spanner.py
- Vertex AI RAG: vertexai_rag_engine.py
Agents
Documentation
Python Examples
- Custom Agent (StoryFlow): storyflow_agent.py
- LLM Agent (Capital): capital_agent.py
- Loop Agent (Doc Improv): loop_agent_doc_improv_agent.py
- Parallel Agent (Web Research): parallel_agent_web_research.py
- Sequential Agent (Code Dev): sequential_agent_code_development_agent.py
General Information
Project & Community
Agent to Agent (A2A)
Agents Configuration
Apps
Other
Get Started with Google ADK (Python)
Documentation
Python Examples
Models
Documentation
Python Examples
- Model Configuration (Snippet): Check specific agent examples for model init patterns.
Runtime & Architecture
Runtime
Sessions & State
Context
Other Components
Python Examples
- Memory/State: user_preference.py
Streaming
Documentation
Python Examples
Tools
Documentation
- Tools Overview
- Gemini API Tools:
- Overview
- Google Search
- Code Execution
- Computer Use
- Google Cloud Tools:
- Overview
- BigQuery
- Vertex AI Search
- Data Agent
- Express Mode
- Custom Tools:
- Overview
- Function Tools
- OpenAPI Tools
- Authentication
Python Examples
- Built-in Tools:
- bigquery.py
- code_execution.py
- google_search.py
- vertexai_search.py
- data_agent.py
- Function Tools:
- func_tool.py
- human_in_the_loop.py
- summarizer.py
- OpenAPI Tools:
- openapi_tool.py
- Overview Samples:
- customer_support_agent.py
- weather_sentiment.py
- doc_analysis.py
- toolset_example.py
- Auth:
- tools_and_agent.py
- agent_cli.py
- helpers.py
Tutorials and Samples
Documentation
Python Examples
- Agent Team Tutorial:
- Step 1 Agent
- Step 2 (Anthropic)
- Step 2 (GPT4)
- Step 3 Agent
- Step 5 Agent
- Step 6 Agent
- YouTube Shorts Assistant:
- agent.py
- loop_agent.py
- loop_agent_runner.py
- util.py
- Notebooks:
- Express Mode Weather Agent
- Shop Agent
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
What does google-adk-python help implement?
google-adk-python guides Python developers through Google ADK agent setup including tool registration, session management, multi-turn orchestration, and GenAI model configuration for backend agent services.
Which language does google-adk-python target?
google-adk-python focuses on Python implementations of Google Agent Development Kit patterns rather than JavaScript or REST-only GenAI clients.