Show HN：使用 OAuth 的 AI 代理审批工作流
這篇「Show HN」文章介紹了「Auth for Agents」，一個介於 AI 代理與 OAuth API 之間的代理層，能在執行動作前強制要求人類批准和遵循政策規則，確保了控制權和可審計性。
Navigation Menu
Search code, repositories, users, issues, pull requests...
Provide feedback
We read every piece of feedback, and take your input very seriously.
Saved searches
Use saved searches to filter your results more quickly
To see all available qualifiers, see our documentation.
License
baristaGeek/auth-for-agents
Folders and files
Latest commit
History
Repository files navigation
Auth for Agents
Auth for Agents is a proxy layer between AI agents and OAuth-based APIs that enforces human approval and policy rules before actions are executed. It records every requested action, decision, and token usage for auditability.
Why This is Cool
Once you give an AI agent your OAuth tokens, it can do anything with no oversight. Auth for Agents sits between AI and your services, requiring your approval before actions execute. You maintain full control and get a complete audit trail of everything your AI agents do.
Getting Started
That's it. The AI agent will monitor your Gmail, compose replies, and ask for your approval before sending.
License
MIT
auth-for-agents
About
Resources
License
Uh oh!
There was an error while loading. Please reload this page.
Stars
Watchers
Forks
Releases
Packages
0
Contributors
2
Uh oh!
There was an error while loading. Please reload this page.
Languages
Footer
Footer navigation
相關文章