Zylos-AI
Official@zylos-ai · Singapore
🐙 Zylos (/ˈzaɪ.lɒs/ 赛洛丝) — Give your AI a life. Open-source agent infrastructure for team collaboration.
Agent Skills by Zylos-AI
Showing 14 vetted skills indexed across 1 GitHub repositories.
zylos-aicheck-context
Monitor context window usage, token consumption, and session costs from statusLine JSON.
zylos-aishell
Facilitate interactive command-line chat with an AI model via Unix domain socket.
zylos-aischeduler
Schedule one-time, cron, and interval AI tasks via CLI.
zylos-aiupgrade-claude
Upgrade Claude Code to the latest version with automatic restart.
zylos-aiactivity-monitor
Monitor Claude agent status and restart it after crashes using PM2.
zylos-aicomponent-management
Manage Zylos components via CLI commands and C4 communication channels.
zylos-aicreate-skill
Guide developers through structuring AI skills with SKILL.md and bundled resources.
zylos-aihttp
Host the Zylos web console with Caddy, HTTPS, and health checks.
zylos-aihealth-check
Monitor PM2 services, disk space, and memory usage for anomalies.
zylos-aiweb-console
Enable browser-based chat with Claude via WebSocket and HTTP APIs.
zylos-aicomm-bridge
Route messages between Telegram and Lark channels and the AI model.
zylos-airestart-claude
Restart a Claude Code session after stopping background tasks and syncing memory.
zylos-aizylos-memory
Manage persistent AI agent memory using tiered markdown files.
zylos-ainew-session
Clear the AI conversation context with a /clear command.
Frequently Asked Questions About Zylos-AI
FAQPage SchemaWhat specific tasks can be managed using Zylos-AI?▼
Zylos-AI enables the management of Claude sessions, including restarting crashed processes, clearing conversation context, and monitoring token consumption. It facilitates cross-platform message routing between Telegram and Lark, manages persistent memory via markdown files, and provides web-based console access secured by Caddy and HTTPS.
Which personas benefit from implementing Zylos-AI infrastructure?▼
System administrators, DevOps engineers, and developers managing Claude-based deployments benefit from these capabilities. It is designed for teams requiring persistent, reliable, and monitored model interactions across distributed messaging platforms and browser-based interfaces, ensuring high availability through process monitoring and health checks.
What are the prerequisites for running Zylos-AI services?▼
Deployment requires a Unix-based environment with PM2 for process management and Caddy for web server hosting. Users must have Claude Code installed, as the infrastructure relies on its session management, and must configure communication channels for Telegram or Lark integration.