Browse categories
Explore
Fiverr Pro
English
$
USD
I will set up openclaw, hermes, nanoclaw, moltbot ai agent, secure on your vps
Kirill M
About this gig
Got OpenClaw half running, or not sure it is safe to leave on?
Installing it takes an hour. What goes wrong comes after: the agent holds your keys, reads your chats and runs with whatever rights the install gave it. Most setups never look at that.
I install and configure self-hosted agents - OpenClaw, Hermes, NanoClaw, NemoClaw, Moltbot, Clawdbot and similar - on your VPS, Mac or home server, and I lock them down as part of the job.
What you will get:
- A working agent on your own hardware, reachable from Telegram or another channel you choose
- Your LLM connected: Claude, GPT, Gemini or a local model
- Skills installed and tested, not just copied in
- Secrets kept out of the config, firewall rules, and on Premium a container with its own restricted user
- A short document on what runs where and how to restart it
Why work with me:
- Over a hundred commits of mine in an open-source agent runtime of this family, including the tool allowlist and container isolation
- I run these agents daily on my own servers
- Told up front: the LLM is billed to your own account
Message me before ordering with what you want the agent to do and where it should run.
Get to know Kirill M
Kirill M
AI automation engineer, Python, LLM, backend, DevOps, bots
- FromGeorgia
- Member sinceAug 2026
- Last delivery1 month
Languages
Russian, English
I build API integrations and AI automation that run without supervision.
Connecting systems that were never meant to talk - your API, a CRM, a database, a messenger, an LLM - and making the result run on a schedule with nobody watching it.
My own pipeline has published since 2016, rewritten four times: ten LLM providers with automatic failover, ~1,150 items a month unattended.
Before that: 11 years as a Linux systems administrator, up to 200 production servers under a 24/7 SLA.
Most developers hand you the code and leave. Most sysadmins do not write it. I do both, and I keep it running.
My Portfolio
FAQ
Do I need my own server?
Yes, a small VPS is enough, usually around 5 dollars a month. If you do not have one, tell me and I will say exactly what to get, then set it up and deploy on it for you.
What happens when an AI provider goes down?
Nothing stops. Each stage has its own chain of providers, so the next one takes over automatically. In the worst case a single item is handled a bit more simply, instead of your automation going silent.
Can I see it working before I order?
Yes. Message me and I will walk you through the architecture of the system I already run in production, and answer any question about how your case would work.
How is this different from a Zapier or n8n workflow?
For simple chains those are great, and I will tell you if that is all you need. I get called when the workflow hits a wall: custom logic, an API that needs real error handling, an LLM step that must not fail, or something that has to run reliably for months.
