adk-python
https://github.com/google/adk-python
Python
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported2 Subscribers
Add a CodeTriage badge to adk-python
Help out
- Issues
- Feature request: Implement Caching with TTL for McpToolset
- Stop a Running Agent / Edit a previous prompt
- Feature Request: Runtime Configurations with Env Vars
- Feature Request: Agent Evaluations print detailed results even when all tests pass
- Using Copilokit Frontend tools with Orchestrator-style ADK agents
- [BUG] When executing Runners(of which agent contains stateful toolset) in parallel, toolset is being released when only one of them has finished
- Configure context compression per session
- It is hoped that the Agent supports requests for configuring third-party models
- The adk api_server --a2a command failed to retrieve a valid agent_card.
- Tool Hallucination when using ContextWindowCompression and BIDI Live
- Docs
- Python not yet supported