Google ADK Python Skill
Expert guide for Google's Agent Development Kit (ADK) Python — open-source, code-first toolkit for building, evaluating, and deploying AI agents. Optimized for Gemini, model-agnostic by design.
When to Activate
- Build single or multi-agent systems with tool integration
- Implement A2A protocol for remote agent communication
- Integrate MCP servers as agent tools
- Use workflow agents (sequential, parallel, loop) for pipelines
- Manage sessions, state, memory, and artifacts
- Add callbacks, plugins, or observability hooks
- Deploy to Cloud Run, Vertex AI Agent Engine, or GKE
- Evaluate agents with
adk eval framework
Agent Structure Convention (Required)
my_agent/
├── __init__.py # MUST: from . import agent
└── agent.py # MUST: root_agent = Agent(...) OR app = App(...)
Quick Start
pip install google-adk # stable (weekly releases)
uv sync --all-extras # dev setup (uv required, Python 3.10+, 3.11+ recommended)
from google.adk import Agent
root_agent = Agent(
name="assistant",
model="gemini-2.5-flash",
instruction="You are a helpful assistant.",
description="General assistant agent.",
tools=[get_weather],
)
App Pattern (Production)
from google.adk import Agent
from google.adk.apps import App
from google.adk.apps.app import EventsCompactionConfig
from google.adk.plugins.save_files_as_artifacts_plugin import SaveFilesAsArtifactsPlugin
app = App(
name="my_app",
root_agent=Agent(name="my_agent", model="gemini-2.5-flash", ...),
plugins=[SaveFilesAsArtifactsPlugin()],
events_compaction_config=EventsCompactionConfig(compaction_interval=2),
)
Use App when needing plugins, event compaction, or custom lifecycle management.
CLI Tools
| Command |
Purpose |
adk web <agents_dir> |
Dev UI (recommended for development) |
adk run <agent_dir> |
Interactive CLI testing |
adk api_server <agents_dir> |
FastAPI production server |
adk eval <agent> <evalset.json> |
Run evaluation suite |
Agent Types
| Type |
Use Case |
Agent / LlmAgent |
Dynamic routing, tool use, reasoning |
SequentialAgent |
Fixed-order pipeline |
ParallelAgent |
Concurrent execution |
LoopAgent |
Iterative processing |
RemoteA2aAgent |
Remote agent via A2A protocol |
Key APIs
| Feature |
API |
| State |
tool_context.state[key] = value |
| Artifacts |
tool_context.save_artifact(name, part) |
| Callbacks |
before_agent_callback, after_model_callback, etc. |
| MCP Tools |
MCPToolset(connection_params=StdioConnectionParams(...)) |
| Sub-agents |
Agent(..., sub_agents=[agent1, agent2]) |
| Human-in-loop |
LongRunningFunctionTool(func=my_func) |
| Plugins |
App(..., plugins=[MyPlugin()]) |
Model Support
Latest: gemini-2.5-flash (default), gemini-2.5-pro, gemini-2.0-flash (sunsets Mar 2026)
Preview: gemini-3-flash-preview, gemini-3-pro-preview
Also: OpenAI Codex, Ollama, LiteLLM, vLLM, Model Garden
Best Practices
- Code-first — define agents in Python for version control and testing
- Agent convention — always use
root_agent or app variable in agent.py
- Modular agents — specialize per domain, compose via
sub_agents
- Workflow selection — workflow agents for predictable, LlmAgent for dynamic
- State —
ToolContext.state for ephemeral, MemoryService for long-term
- Safety — callbacks for guardrails, tool confirmation for sensitive ops
- Evaluate — test with
adk eval + evalset JSON before deployment
References
Detailed guides (load as needed):
references/agent-types-and-architecture.md — Agent types, workflows, custom agentsreferences/tools-and-mcp-integration.md — Custom tools, MCP, tool filteringreferences/multi-agent-and-a2a-protocol.md — Sub-agents, A2A, coordinator patternsreferences/sessions-state-memory-artifacts.md — State, artifacts, sessions, memoryreferences/callbacks-plugins-observability.md — Lifecycle hooks, plugins, tracingreferences/evaluation-testing-cli.md — adk eval, CLI, evalset formatreferences/deployment-cloud-run-vertex-gke.md — Cloud Run, Vertex AI, GKE
External Resources
1---2name: ck-google-adk-python3description: Build AI agents with Google ADK Python. Multi-agent systems, A2A protocol, MCP tools, workflow agents, state/memory, callbacks/plugins, Vertex AI deployment, evaluation.4license: Apache-2.05---67# Google ADK Python Skill89Expert guide for Google's Agent Development Kit (ADK) Python — open-source, code-first toolkit for building, evaluating, and deploying AI agents. Optimized for Gemini, model-agnostic by design.1011## When to Activate1213- Build single or multi-agent systems with tool integration14- Implement A2A protocol for remote agent communication15- Integrate MCP servers as agent tools16- Use workflow agents (sequential, parallel, loop) for pipelines17- Manage sessions, state, memory, and artifacts18- Add callbacks, plugins, or observability hooks19- Deploy to Cloud Run, Vertex AI Agent Engine, or GKE20- Evaluate agents with `adk eval` framework2122## Agent Structure Convention (Required)2324```25my_agent/26├── __init__.py # MUST: from . import agent27└── agent.py # MUST: root_agent = Agent(...) OR app = App(...)28```2930## Quick Start3132```bash33pip install google-adk # stable (weekly releases)34uv sync --all-extras # dev setup (uv required, Python 3.10+, 3.11+ recommended)35```3637```python38from google.adk import Agent3940root_agent = Agent(41 name="assistant",42 model="gemini-2.5-flash",43 instruction="You are a helpful assistant.",44 description="General assistant agent.",45 tools=[get_weather],46)47```4849## App Pattern (Production)5051```python52from google.adk import Agent53from google.adk.apps import App54from google.adk.apps.app import EventsCompactionConfig55from google.adk.plugins.save_files_as_artifacts_plugin import SaveFilesAsArtifactsPlugin5657app = App(58 name="my_app",59 root_agent=Agent(name="my_agent", model="gemini-2.5-flash", ...),60 plugins=[SaveFilesAsArtifactsPlugin()],61 events_compaction_config=EventsCompactionConfig(compaction_interval=2),62)63```6465Use `App` when needing plugins, event compaction, or custom lifecycle management.6667## CLI Tools6869| Command | Purpose |70|---------|---------|71| `adk web <agents_dir>` | Dev UI (recommended for development) |72| `adk run <agent_dir>` | Interactive CLI testing |73| `adk api_server <agents_dir>` | FastAPI production server |74| `adk eval <agent> <evalset.json>` | Run evaluation suite |7576## Agent Types7778| Type | Use Case |79|------|----------|80| `Agent` / `LlmAgent` | Dynamic routing, tool use, reasoning |81| `SequentialAgent` | Fixed-order pipeline |82| `ParallelAgent` | Concurrent execution |83| `LoopAgent` | Iterative processing |84| `RemoteA2aAgent` | Remote agent via A2A protocol |8586## Key APIs8788| Feature | API |89|---------|-----|90| State | `tool_context.state[key] = value` |91| Artifacts | `tool_context.save_artifact(name, part)` |92| Callbacks | `before_agent_callback`, `after_model_callback`, etc. |93| MCP Tools | `MCPToolset(connection_params=StdioConnectionParams(...))` |94| Sub-agents | `Agent(..., sub_agents=[agent1, agent2])` |95| Human-in-loop | `LongRunningFunctionTool(func=my_func)` |96| Plugins | `App(..., plugins=[MyPlugin()])` |9798## Model Support99100Latest: `gemini-2.5-flash` (default), `gemini-2.5-pro`, `gemini-2.0-flash` (sunsets Mar 2026)101Preview: `gemini-3-flash-preview`, `gemini-3-pro-preview`102Also: OpenAI Codex, Ollama, LiteLLM, vLLM, Model Garden103104## Best Practices1051061. **Code-first** — define agents in Python for version control and testing1072. **Agent convention** — always use `root_agent` or `app` variable in `agent.py`1083. **Modular agents** — specialize per domain, compose via `sub_agents`1094. **Workflow selection** — workflow agents for predictable, LlmAgent for dynamic1105. **State** — `ToolContext.state` for ephemeral, `MemoryService` for long-term1116. **Safety** — callbacks for guardrails, tool confirmation for sensitive ops1127. **Evaluate** — test with `adk eval` + evalset JSON before deployment113114## References115116Detailed guides (load as needed):117118- `references/agent-types-and-architecture.md` — Agent types, workflows, custom agents119- `references/tools-and-mcp-integration.md` — Custom tools, MCP, tool filtering120- `references/multi-agent-and-a2a-protocol.md` — Sub-agents, A2A, coordinator patterns121- `references/sessions-state-memory-artifacts.md` — State, artifacts, sessions, memory122- `references/callbacks-plugins-observability.md` — Lifecycle hooks, plugins, tracing123- `references/evaluation-testing-cli.md` — adk eval, CLI, evalset format124- `references/deployment-cloud-run-vertex-gke.md` — Cloud Run, Vertex AI, GKE125126## External Resources127128- GitHub: https://github.com/google/adk-python129- Docs: https://google.github.io/adk-docs/130- Samples: https://github.com/google/adk-python/tree/main/contributing/samples131- llms.txt: https://raw.githubusercontent.com/google/adk-python/refs/heads/main/llms.txt
manhvann