How to use Adk Python: what you can do with it

3 use cases

• Build an agent and test it in ADK's web UI

  Define an agent in a few lines of Python and chat with it in the built-in development UI.

  • REPO google/adk-python
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • Software and DevOps
  • Beginner
  View prompt

  Using google/adk-python, create an agent folder with a root_agent that <describe job>, give it <tools>, and run it with `adk web path/to/agents_dir`. Show me a test conversation and the tool calls it made.

  Share Email me this

• Chain agents into a deterministic workflow

  Use ADK's Workflow runtime to pass work between specialised agents in a fixed graph.

  • REPO google/adk-python
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • Software and DevOps
  • Intermediate
  View prompt

  With google/adk-python, build a Workflow where <agent A> does <step 1> and passes its output to <agent B> for <step 2>. Add a retry on <step> and a human-in-the-loop check before <final step>, then run it in adk web.

  Share Email me this

• Evaluate an agent and deploy it to Cloud Run

  Run ADK's evaluation against a test set, then ship the agent in a container or on Cloud Run with one command.

  • REPO google/adk-python
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • Software and DevOps
  • Intermediate
  View prompt

  Using google/adk-python, write an evalset for my agent covering <cases>, run adk eval and report failures. If it passes, deploy it with `adk deploy cloud_run --with_ui` and give me the URL.

  Share Email me this

Quick start with Adk Python

1. Check you have what it needs: Python 3.11 or later; pip; A model to call, such as Gemini; ADK is model-agnostic.
2. Open google/adk-python on GitHub and read the README and license.
3. Install with pip install google-adk (Python 3.11+)
4. Create an Agent with a name, model and instruction, as in the Quick Start, and assign it to root_agent
5. Chat with it in the terminal with adk run path/to/my_agent
6. Open the development UI with adk web path/to/agents_dir to test, debug and showcase it

These steps come from our top use case, Build an agent and test it in ADK's web UI, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for google/adk-python

claude mcp add --transport http deduped https://dedupedai.com/mcp

Best AI repos for Software and DevOps

About this repo

• Who it is forPython developers building agents or multi-agent systems, especially on Google Cloud, who want testing and deployment built in.
• Why it is hot22k stars, talked about in 2 AI sources we track
• LanguagePython
• Sourcegithub.com/google/adk-python · Back to Hot repos

Requirements

• Python 3.11 or later
• pip
• A model to call, such as Gemini; ADK is model-agnostic
• For Cloud Run deploys: a Google Cloud project; for local containers: Docker

Related repos

• Trended earlier REPO google-gemini/gemini-cli Gemini CLI Gemini CLI is Google's open-source AI agent for the terminal. It reads your codebase, runs commands and answers prompts with Gemini models, and can run headless with JSON or streaming JSON output for scripts and CI. The README notes that unpaid tier and Google One users were moved to Antigravity CLI on June 18, 2026 and that Gemini CLI is not optimized for the newest Gemini models, so it now fits API key and Vertex AI users best.
• Trended earlier REPO scaleapi/agentenv-framework Agentenv Framework AgentEnv Framework is a Python SDK and CLI for building, deploying and running containerized agentic environments and the tasks that grade agents inside them.
• Trended earlier REPO aaravshah1311/Agent-2 Agent 2 Agent-2 is a Python agent harness that runs on your machine with your own Gemini API keys and can write code, run terminal commands, manage files, and coordinate tools.