agentos-sdk
par agentossoftware
DevOps & CloudRésumé
AgentOS is a complete accountability infrastructure for AI.
Description
Ce que fait ce skill
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.
Quand l'utiliser
- 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
Exemple de workflow
User asks: save today's learnings and check for past OAuth mistakes
- 1
Sources agentos.sh and sets AGENTOS_API_KEY, AGENTOS_BASE_URL, and AGENTOS_AGENT_ID
- 2
Calls aos_put with AOS_SEARCHABLE=true to store the learning under /memory/learnings/2026-03-12
- 3
Calls aos_search with query "OAuth mistakes" to find relevant past memories
- 4
Returns results ranked by semantic similarity
Learning stored at /memory/learnings/2026-03-12 and past OAuth-related mistakes retrieved ranked by relevance
Prérequis
- AGENTOS_API_KEY from the agentos.software dashboard
- AGENTOS_AGENT_ID for the agent instance
- AGENTOS_BASE_URL pointing to the AgentOS API endpoint
Installation
clawhub install agentossoftware/agentos-sdkExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.