48-scenario benchmark testing identity, policy enforcement, and observability across AI agent runtimes.
-
Updated
Jul 13, 2026 - Python
#
tool-permissions
Here are 2 public repositories matching this topic...
TypeScript + Python SDKs for scope-narrowed subagents and delegation chains — every action audits back to the originating human. Anthropic SDK, CrewAI, LangChain.
-
Updated
Jul 17, 2026 - Python
Improve this page
Add a description, image, and links to the tool-permissions topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the tool-permissions topic, visit your repo's landing page and select "manage topics."