#87 · Primary category: AI Agents & Automation

adk-python

agent agentic agentic-ai agents agents-sdk ai ai-agents aiagentframework genai genai-chatbot llm llms multi-agent multi-agent-systems multi-agents multi-agents-collaboration

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

Project last updated:08/29/26

GitHub Stars

21.3K

Forks

3.9K

Contributors

466

License

Apache-2.0

Why we included this project

Google's Agent Development Kit lets you build agents as plain Python code that lives in version control, rather than clicking through a visual builder. You define an agent with its model, instructions, and tools, then wire several of them into a graph-based workflow that handles routing, retries, loops, and human-in-the-loop checkpoints. That combination is useful when you want deterministic orchestration on top of LLM behavior instead of a single chatbot. The 2.0 release adds a Task API for structured agent-to-agent delegation, which helps when you split work across specialized sub-agents but still need controlled outputs. Evaluation tooling and a local web UI round it out, so you can run and inspect multi-agent setups before pushing them to production.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category