Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
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 |
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
The English summary is being prepared. Showing the original description.
Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.