본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

agentos-sdk

agentossoftware 제작

DevOps & Cloud
1.5kclawskills.sh가 보고한 다운로드 수
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

AgentOS is a complete accountability infrastructure for AI.

설명

이 스킬이 하는 일

AgentOS is a persistent memory and communication infrastructure for AI agents, delivered as a bash SDK. It handles storing, tagging, and semantically searching memories across sessions, along with project tracking, kanban boards, activity logging, and agent-to-agent messaging via a mesh layer.

Combines persistent memory, semantic search, project management, and inter-agent messaging in one SDK, removing the need to wire up separate tools for each concern.

사용 시점

  • Storing agent learnings and mistakes between sessions
  • Tracking project tasks on a per-agent kanban board
  • Sending messages between two running AI agents
  • Caching API responses with automatic TTL expiration
  • Logging daily agent activity for later review

예시 워크플로

입력

User asks: save today's learnings and check for past OAuth mistakes

에이전트
  1. 1

    Sources agentos.sh and sets AGENTOS_API_KEY, AGENTOS_BASE_URL, and AGENTOS_AGENT_ID

  2. 2

    Calls aos_put with AOS_SEARCHABLE=true to store the learning under /memory/learnings/2026-03-12

  3. 3

    Calls aos_search with query "OAuth mistakes" to find relevant past memories

  4. 4

    Returns results ranked by semantic similarity

출력

Learning stored at /memory/learnings/2026-03-12 and past OAuth-related mistakes retrieved ranked by relevance

요구 사항

  • AGENTOS_API_KEY from the agentos.software dashboard
  • AGENTOS_AGENT_ID for the agent instance
  • AGENTOS_BASE_URL pointing to the AgentOS API endpoint

설치

clawhub install agentossoftware/agentos-sdk

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크