Ross ROSS = Recommend OSS · open-source software intelligence for agents

Agent Development Kit (ADK)

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control. observed · 2026-08-28

github.com/google/adk-python · homepage · Python · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

82/100

  • Activity 99
  • Release rhythm 87
  • Longevity 37
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 6.0
  • age_days: 519
  • days_rel: 7
  • days_push: 7
  • n_releases_24m: 79

Full methodology

Adoption not part of the score

21299 stars · 3897 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Agent Development Kit (ADK) is Google's open-source, code-first framework for building, evaluating, and deploying AI agents, available in Python, TypeScript, Go, Java, and Kotlin. It provides a graph-based workflow runtime, tool integration, session/memory management, and A2A protocol support for multi-agent systems, optimized for Gemini but model- and deployment-agnostic.

Use cases

  • build a conversational AI agent with tools like web search
  • orchestrate multi-agent workflows with sequential and parallel steps
  • expose my agent to other agents via the A2A protocol
  • add human-in-the-loop approval steps to an agentic pipeline
  • evaluate and debug LLM agents before deploying to production
  • build a customer support chatbot backed by an LLM
  • deploy agents at enterprise scale on Google Cloud

When to choose

  • you want a code-first, production-oriented agent framework with strong tooling
  • you need multi-agent orchestration with deterministic workflow control
  • you're building primarily with Gemini but want model flexibility
  • you need A2A interoperability between agents across services
  • you want official Google support and multi-language SDKs

When to avoid

  • you want a minimal single-file agent script with zero framework overhead
  • you're locked into a non-Google ecosystem with its own agent SDK
  • you need a no-code/low-code agent builder rather than writing code
  • your project depends on ADK 1.x APIs incompatible with 2.0 breaking changes

Facets

framework · maturity active

agent-framework llm-inference workflow-automation chatbot rag mcp sdk cli developer-tools large-language-models artificial-intelligence developer-tools python go jvm cross-platform cli cloud multi-agent-systems a2a-protocol gemini model-agnostic code-first google agent-evaluation graph-workflows human-in-the-loop ai-agents automation nodejs docker

10 sources

Member repositories

RepositoryRoleHealth v2
google/adk-pythonmain82
google/adk-samplesexamples64
google/adk-gosdk85
google/adk-javasdk86
google/adk-docsdocs64
google/adk-jssdk84
google/adk-webfrontend85

For agents

markdown · JSON · MCP: product_card(name="google/adk-python")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem