Search

More Filters

Show More
Add Listing
Go Back

adk python

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

Agent Development Kit (ADK) is an open-source, code-first Python toolkit for building, evaluating, and deploying AI agents. It is designed for developers to create agentic architectures that range from simple assistants to complex, multi-agent workflows. While optimized for Gemini and integration with the Google ecosystem, ADK is model-agnostic and deployment-agnostic and aims to make agent development feel more like standard software development by enabling Python-defined agent logic, tools, and orchestration. The project includes documentation, sample repositories, a Java ADK and a web UI companion, and provides both stable PyPI releases and a development install from the main branch. ADK targets development teams who need modular, testable, and versioned approaches to create and operate agents across environments.

Links

Stars
12112
App URL
https://github.com/google/adk-python
Github Repository
https://github.com/google/adk-python/blob/main/README.md

Categorization

App Details

Features
ADK provides a rich tool ecosystem with pre-built tools and support for custom functions and OpenAPI specs so agents can call external capabilities. It emphasizes code-first development so agent logic, tools, and orchestration are defined directly in Python for flexibility, testability, and version control. The framework supports modular multi-agent systems allowing composition of specialized agents and hierarchical coordination. Deployment is flexible, enabling containerization and deployment to Cloud Run or scaling with Vertex AI Agent Engine. ADK integrates with the Agent2Agent (A2A) protocol for remote agent-to-agent communication. Additional features include a built-in development UI for testing and debugging, command-line evaluation tooling, and a library of samples and documentation.
Use Cases
ADK helps developers by providing a structured framework and reusable components that reduce boilerplate when building agents and multi-agent systems. By defining agents and tools in Python, teams can apply normal software engineering practices such as testing, versioning, and modular design. Integration with pre-built tools and OpenAPI specs accelerates capability integration and the A2A protocol enables distributed agent communication. Built-in tooling such as a development UI and evaluation commands supports debugging, iteration, and benchmarking. Deployment guidance and compatibility with Cloud Run and Vertex AI Agent Engine make it easier to move from development to production. The project also offers documentation, samples, and a clear contribution path for extending functionality.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*