多雲端、框架無關的 AI 代理執行環境，用於在 OpenAI、CrewAI、LangGraph 和 Google ADK 上建置、測試和部署生產級代理。
yaalalabs/agent-kernel 是一款多雲端、框架無關的 AI 代理執行環境，專為開發者設計，用於建置、測試及部署生產就緒的 AI 代理。它支援多種流行框架，包括 OpenAI、CrewAI、LangGraph 和 Google ADK，讓開發者能將相同的代理程式碼無縫部署至 AWS 或 Azure。此技能的核心優勢在於其內建功能，例如工作階段管理、執行掛鉤、MCP/A2A 協議支援、護欄機制、可觀測性以及容錯處理，從而簡化生產環境中 AI 代理的維運。對於需要在多雲端環境中運行一致代理行為的團隊而言，這項技能可大幅降低跨平台遷移的複雜性，並確保系統的可靠性與可維護性。其設計初衷是解決代理從開發到部署過程中的常見痛點，特別是在處理不同雲端供應商和代理框架的相容性問題上。
npx skills add yaalalabs/agent-kernelInstalled? Explore more 程式設計與開發 skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
Multi-cloud, framwork-agnostic AI agent runtime for building, testing, and deploying production agents across OpenAI, CrewAI, LangGraph, and Google ADK. Deploy the same agent code to AWS or Azure with built-in session management, execution hooks, MCP/A2A support, guardrails, observability and fault tolerance.
Source: https://github.com/yaalalabs/agent-kernel
Discovered during the daily awesomeskills.dev agent-skill hunt.
Send and manage iMessages via BlueBubbles, including attachments, tapbacks, edits, replies, and groups.
Control Eight Sleep pods (status, temperature, alarms, schedules).
BluOS CLI (blu) for discovery, playback, grouping, and volume.
Create, search, and manage Bear notes via grizzly CLI.
Capture frames or clips from RTSP/ONVIF cameras.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.