Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
中文简介正在准备中。当前显示原文说明。
Browse, preview, and install AOS Core, ECC and Scenario skills and agents from a local web UI. Use when exploring or adding new skills to a project.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
A web UI for discovering and installing AOS skills and agents. Lists what is already installed, previews new items before adding them, and confirms every install explicitly.
The store can be run standalone or inside the AOS Hub. Run aos-store ui to start the local store server; it prints the URL (default http://127.0.0.1:4322), opens your browser unless --no-open is set, and runs in the foreground. Alternatively start aos hub (same security model, port 7900) and open the store's tab there — the hub embeds the store UI, nothing else changes.
# Start the store UI (opens browser automatically)
aos-store ui
# Start the store as a tab of the AOS Hub
aos hub
# Start with a custom port
AOS_STORE_PORT=5000 aos-store ui
# Roll back the most recent install of a named item (every target and backup
# is re-validated first; nothing is ever deleted)
aos store rollback <skill-name>
Confirmations are typed, not clicked: writes need the exact name spelled back (confirm), and stopping or restarting a service through the hub CLI needs --confirm <id>. Nothing is installed or rolled back silently.
Fallback (if aos-store is not on PATH):
npx -p @hybridlabor-api/aos aos-store ui
Some harnesses (e.g. OpenCode) cannot open a browser automatically. Always print the store URL in chat (e.g., http://127.0.0.1:4322) so the user can click it manually.
hooks/ folder are copied only; their hooks are not registered in your harness settings (the preview warns).Check if the store server is running:
curl http://127.0.0.1:4322/api/health
Returns 200 OK if healthy.
The store runs in the foreground. Stop it with Ctrl-C. No separate stop command is available.
| Variable | Purpose | Default |
|---|---|---|
AOS_STORE_PORT | Server port | 4322 |
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
中文简介正在准备中。当前显示原文说明。
Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
中文简介正在准备中。当前显示原文说明。
Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.
中文简介正在准备中。当前显示原文说明。
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.
中文简介正在准备中。当前显示原文说明。
Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
中文简介正在准备中。当前显示原文说明。
agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.
中文简介正在准备中。当前显示原文说明。