#3333rd of 82 in Agent frameworks and SDKs
adk-go
Code-first Go toolkit for building and orchestrating multi-agent applications
- Stars
- 8.9k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Go
7,404 on 10 Apr 20268,916 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
ADK Go is Google's Agent Development Kit for Go, installed as the module google.golang.org/adk/v2. Agent logic, tools and multi-agent composition are defined directly in Go code. It is optimized for Gemini but described as model-agnostic and deployment-agnostic, with containerized deployment aimed at Google Cloud Run.
Who it is for: Go developers building cloud-native LLM agents, especially on Gemini
Strengths
- Agents, tools and orchestration are plain Go, so they can be tested and versioned like other code
- Composes multiple specialized agents into larger systems
- Sibling ADKs exist for Python, Java, Kotlin and TypeScript
- Apache-2.0 licensed, with recent commits and a release in October 2026
Weaknesses
- README names no model providers besides Gemini optimization
- Requires a very recent Go toolchain (1.26.10 or later)
- README has no code example or quickstart, only links to docs and samples
- Deployment guidance in the README centers on Google Cloud Run
What it needs
- Needs Go 1.26.10+
- Models: Gemini
Quick answers
Is adk-go open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Also in Agent frameworks and SDKs
See all 82| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 90 out of 100 |
| 3 | langchainPython framework for building LLM agents and apps from interoperable components | 89 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| #5 | tradingagentsMulti-agent LLM framework that simulates a trading firm's analysis process | 89 out of 100 |