A solo consultant wants a private Telegram assistant for research requests and must decide who may message it.
Explore by goal
AI agents & assistants
Choose an agent, its model provider and the channel or workspace where people will use it.
54 catalog entries across 1 category · 6 related published guides
Start with a situation
What brings you here?
A product team repeats a troubleshooting runbook and wants to evaluate an agent that can retain useful procedures across sessions.
A short decision path
Choose the next step
Compare a chat gateway such as OpenClaw with Hermes Agent’s memory and skills model for the actual task.
Check the dedicated server, model credential, channel and operator-access requirements in the product setup guide.
Run a private acceptance conversation, inspect the agent’s allowed tools and plan updates, backup and recovery.
Hosting options
Explore hosted agents
Compare setup and access requirements before choosing an agent.
From the xCloud app catalog
Applications to explore
Compare these examples, then check setup and availability for the app you choose.
AI
OpenClaw
Run your personal AI assistant with updates, backups, firewall and more. No Docker, no hassle — it runs 24/7 on WhatsApp, Telegram, Slack and Discord.
Read app detailsAI
Hermes Agent
Deploy Hermes Agent in 5 minutes with persistent memory, connected to Telegram, tools, files, APIs and scheduled tasks. No server setup, no resets.
Read app detailsAI
Paperclip
Run an autonomous AI company with org charts, budgets and governance. Hire OpenClaw, Claude Code or Codex agents, live in minutes.
AI
OpenWebUI
Customizable web interface for AI models, connecting to Ollama and any OpenAI-compatible API endpoint.
More options
Included categories
- AI54 entries
Practical guides
Guides to continue with
Start with these related workflows, then check setup requirements for your chosen app.
- Verify a private first task on managed OpenClaw
Launch an eligible managed OpenClaw instance and verify a bounded private task.
- Research a question with OpenClaw and verify sources
Research a public question and verify each source-backed claim.
- Run a bounded OpenClaw scheduled digest
Test a scheduled digest and reconcile its actual delivery.
- Deploy Hermes and verify the first model-backed task
Deploy managed Hermes and verify a harmless model-backed task.
- Send a daily research briefing to Telegram
Build a source-checked daily briefing and verify its scheduled delivery.
- Turn a repeated team task into a Hermes skill
Create a reusable procedure and verify that Hermes loads the intended skill.