{"id":29136331,"url":"https://github.com/sushant1827/google_adk","last_synced_at":"2026-03-06T04:32:35.393Z","repository":{"id":291380943,"uuid":"977444873","full_name":"sushant1827/Google_ADK","owner":"sushant1827","description":"This repository contains examples for learning Google's Agent Development Kit (ADK), a powerful framework for building LLM-powered agents.","archived":false,"fork":false,"pushed_at":"2025-05-27T10:44:55.000Z","size":108,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-27T11:40:42.619Z","etag":null,"topics":["agentic-workflow","google-adk","litellm","multi-agent-system","persistent-storage","pydantic","session-storage","structured-output"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sushant1827.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-04T08:19:35.000Z","updated_at":"2025-05-27T10:44:58.000Z","dependencies_parsed_at":null,"dependency_job_id":"adad12b5-3f65-4c46-9217-0848cd32fec0","html_url":"https://github.com/sushant1827/Google_ADK","commit_stats":null,"previous_names":["sushant1827/google_adk"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/sushant1827/Google_ADK","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sushant1827%2FGoogle_ADK","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sushant1827%2FGoogle_ADK/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sushant1827%2FGoogle_ADK/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sushant1827%2FGoogle_ADK/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sushant1827","download_url":"https://codeload.github.com/sushant1827/Google_ADK/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sushant1827%2FGoogle_ADK/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262762465,"owners_count":23360330,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic-workflow","google-adk","litellm","multi-agent-system","persistent-storage","pydantic","session-storage","structured-output"],"created_at":"2025-06-30T11:07:42.793Z","updated_at":"2026-03-06T04:32:35.339Z","avatar_url":"https://github.com/sushant1827.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Agent Development Kit (ADK) Crash Course\n\nThis repository contains examples for learning Google's Agent Development Kit (ADK), a powerful framework for building LLM-powered agents.\n\n## Getting Started\n\n### Setup Environment\n\nYou only need to create one virtual environment for all examples in this course. Follow these steps to set it up:\n\n```bash\n# Create virtual environment in the root directory\npython -m venv .venv\n\n# Activate (each new terminal)\n# macOS/Linux:\nsource .venv/bin/activate\n# Windows CMD:\n.venv\\Scripts\\activate.bat\n# Windows PowerShell:\n.venv\\Scripts\\Activate.ps1\n\n# Install dependencies\npip install -r requirements.txt\n```\n\nOnce set up, this single environment will work for all examples in the repository.\n\n### Setting Up API Keys\n\n1. Create an account in Google Cloud https://cloud.google.com/?hl=en\n2. Create a new project\n3. Go to https://aistudio.google.com/apikey\n4. Create an API key\n5. Assign key to the project\n6. Connect to a billing account\n\nEach example folder contains a `.env.example` file. For each project you want to run:\n\n1. Navigate to the example folder\n2. Rename `.env.example` to `.env` \n3. Open the `.env` file and replace the placeholder with your API key:\n   ```\n   GOOGLE_API_KEY=your_api_key_here\n   ```\n\nYou'll need to repeat this for each example project you want to run.\n\n## Examples Overview\n\nHere's what you can learn from each example folder:\n\n### 1. Basic Agent\nIntroduction to the simplest form of ADK agents. Learn how to create a basic agent that can respond to user queries.\n\n### 2. Tool Agent\nLearn how to enhance agents with tools that allow them to perform actions beyond just generating text.\n\n### 3. LiteLLM Agent\nExample of using LiteLLM to abstract away LLM provider details and easily switch between different models.\n\n### 4. Structured Outputs\nLearn how to use Pydantic models with `output_schema` to ensure consistent, structured responses from your agents.\n\n### 5. Sessions and State\nUnderstand how to maintain state and memory across multiple interactions using sessions.\n\n### 6. Persistent Storage\nLearn techniques for storing agent data persistently across sessions and application restarts.\n\n### 7. Multi-Agent\nSee how to orchestrate multiple specialized agents working together to solve complex tasks.\n\n### 8. Stateful Multi-Agent\nBuild agents that maintain and update state throughout complex multi-turn conversations.\n\n### 9. Callbacks\nImplement event callbacks to monitor and respond to agent behaviors in real-time.\n\n### 10. Sequential Agent\nCreate pipeline workflows where agents operate in a defined sequence to process information.\n\n### 11. Parallel Agent\nLeverage concurrent operations with parallel agents for improved efficiency and performance.\n\n### 12. Loop Agent\nBuild sophisticated agents that can iteratively refine their outputs through feedback loops.\n\n## Official Documentation\n\nFor more detailed information, check out the official ADK documentation:\n- https://google.github.io/adk-docs/get-started/quickstart\n\n## Support\n\nNeed help or run into issues? Join our free AI Developer Accelerator community on Skool:\n- [AI Developer Accelerator Community](https://www.skool.com/ai-developer-accelerator/about)\n\nIn the community you'll find:\n- Weekly coaching and support calls\n- Early access to code from YouTube projects\n- A network of AI developers of all skill levels ready to help\n- Behind-the-scenes looks at how these apps are built\n\n## Error handling\n\n### 1.  If you're seeing a blank web page after running adk web, here’s something that might help. \n   https://github.com/google/adk-python/issues/114\n\n   Adding the below to fast_api.py (.venv\\Lib\\site-packages\\google\\adk\\cli) fixed the blank issue for me\n\n   import mimetypes\n\n   mimetypes.add_type(\"text/javascript\", \".js\", True)\n\n   Don't forget to clear your browser cache after making above changes.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsushant1827%2Fgoogle_adk","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsushant1827%2Fgoogle_adk","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsushant1827%2Fgoogle_adk/lists"}