AgentsOpen Source$5/monthActiveLocal hardware· advanced · ~60 min setup
Self-Hosted Self-Improving Agent with Hermes
Stand up a Hermes agent that remembers and improves over time on your own VPS.
Run this workflow
See exactly what it produces before you build it.
Build this with your agent
One copy-paste hands Claude Code, Codex, or Cursor the full recipe, steps included, nothing to fetch.
Intended Use
Power users wanting an agent they fully own, memory, prompts, model choice, on their own infrastructure.
Not for
- Single-task one-off prompts (overkill)
- Users without VPS/Docker experience
The Stack
Tested Against
hermes@0.12.0hetzner-cx22ollama@0.5Side effects & data flow
- Network
- hetzner.com, ollama.com
- Writes
- /var/hermes/, ~/.ssh/known_hosts
- Credentials
- HETZNER_SSH_KEY
Prerequisites
- A Hetzner VPS
- Docker
Steps
- 1
Provision the VPS
Spin up a Hetzner box and install Docker.
ssh root@your-vps 'curl -fsSL https://get.docker.com | sh' - 2
Deploy Hermes
Run the Hermes container with a persistent volume for memory.
Eval, 1 fixture
Last passed: verified 1mo agohealth-checkcontainstimeout 60s · max $0Expected:
ok
Results
47 comments on the original post; replaces a stack of paid agent services.
Did this work for you?
Our CI checks the setup runs. You tell us if the whole thing worked. Tell us straight.
Related workflows
- Prove your meeting-notes pipeline never phones home (and gates on consent)
- Validate a WrenAI semantic model's references before an agent queries through it
- Wire the DeepWiki MCP into your agent so it looks up repos instead of hallucinating
- Verify an agent-skills plugin before you ship or install it
- WebMCP: declare a site's agent tools, and gate the ones that spend money
- Wire GLM-5.2 into Hermes: valid route, 64k-context check, no key in config
Liked this workflow?
Get new verified workflows in WebAfterAI, three issues a week (Tue, Thu, Sat).