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
- fix(models): populate model_version on AnthropicLlm responses
- fix(models): populate LlmResponse.model_version in AnthropicLlm
- fix: preserve Anthropic model version in streaming and non-streaming responses
- AnthropicLlm never populates LlmResponse.model_version
- fix(models): route interleaved interactions function-call deltas by step index
- feat(cli): add `adk eval --num_runs N` with per-eval-case aggregation
- feat(runners): stop a live agent and edit a previous prompt
- feat(agents): let nested LoopAgents exit independently
- fix(a2a): render a historical function response as text
- fix(agents): accept generation kwargs on LlmAgent
- Docs
- Python not yet supported