My Homelab AI Dev Platform (rsgm.dev)
66 points by rsgm 3 hours ago
MisterPea 4 minutes ago
Some times I feel like a lot of people in tech independently go through the same things right around the same time with few people writing/sharing about it.
I am also creating this and enjoyed the post and comments all going through the same thing :)
david-giesberg 33 minutes ago
I've been doing something pretty similar, except instead of having a persistent opencode server, I've been using this workflow that runs opencode inside of the Forgejo action runners:
https://codeberg.org/dragonfyre13/forgejo-opencode
Still tinkering with it, but the gist is that I can invoke Opencode with /oc inside of an Forgejo issue, then it will come back with a PR for me to review.
doctorspazz an hour ago
I've been trying to find the motivation to do a write up on my AI lab, and this is just what I needed. Thanks for sharing. My setup is a similar idea, just with n8n/git/argo/k3s. It's mainly for automated workflows that Qwen or Gemma4 can handle.
dlxfoo an hour ago
Im doing something very similar. Running my OpenCode on a proxmox lxc. I have an additional layer of Kimaki, which gives you Discord integration (hate it or love it). Chatting with your codebase (voice messages, too, if that’s your jam), is very very cool.
rsgm an hour ago
That's very cool. Thanks, I'll have to check that out.
taleodor an hour ago
Very cool, we're doing similar except we let agents open PRs as well + we track release metadata and agentic sessions via our ReARM system + we've recently launched an option for agents to track helm-based deployments via ReARM - https://docs.rearmhq.com/workflows/devops.html
rsgm an hour ago
I didn't mention this part, but while writing this I realized I could easily add a skill to hit the Forgejo PR API. There's no forgejo CLI like there is with GitHub sadly.
cosnenc 20 minutes ago
mfenniak 12 minutes ago
bityard 43 minutes ago
That seems like a problem an LLM could solve. ;) (Assuming Forgejo has a reasonable REST/whatever API.)
variety8675 an hour ago
How do you run inference for Open Code? What models are you running
_def an hour ago
I wonder how gitops is done with docker compose
stryan an hour ago
I see a lot of people using Komodo for it, though if I had to pick I'd go with Doco CD[0]. You can also use standard Ansible for just cron+bash script to git pull.
On the Podman side, I wrote a tool named Materia[1] for it, but there's also the wonderful Ansible quadlet role as well as Quadit and Orchess.
[0] https://github.com/kimdre/doco-cd
[1] https://primamateria.systems or https://github.com/stryan/materia
rsgm an hour ago
I recently setup Arcane and started migrating stuff from Truenas apps, they were all deployed as custom docker compose services so it worked out. Arcane supports Git syncs to auto deploy compose stacks, https://getarcane.app/docs/features/projects#sync-from-git I'll write up some posts on my full setup soon.
blumomo 36 minutes ago
What _IS_ Arcane? I fail to understand from their website https://getarcane.app/
Is it a deployment automation platform where it can run a project’s docker services, with rollback and all?
rsgm 21 minutes ago
fazgha an hour ago
So first post in the blog, and it went directly HN frontpage.
Then, I said homelab AI, I thought it's an interesting post about local GPU setup (and I am really interested in this topic).. but no, just another hype post about how to use whatever-code...
rsgm an hour ago
I looked into running local models last month. They just aren't quite there for agentic tool use workflows without spending a small fortune. I'm hopeful smaller local models get much better soon.
I was also hoping to put out another post on my homelab setup, it has some neat stuff, but I haven't had a chance to finish it.
sosodev an hour ago
I think it heavily depends on what you're asking the model to do. Qwen3.6, both 27B and 35B-A3B, do agentic tool use very well. Their decision making is sus, but the dense model is decent in that way. A 4-bit quant for either of those can run on many home systems with a bit of configuration.
The biggest issue I've noticed is that the chat templates for open models are really hit or miss. The default Qwen3.6 chat template mostly works these days, but depending on your workload it may cause major issues. There are plenty of "fixed" chat templates on hugging face, but people report mixed success. It really seems to depend a lot on what the tool you're using expects.
reactordev an hour ago
you can't explain the HN hug. You feel it, or your servers do.
johnnytech 2 hours ago
Really cool! Do you autoapprove edits or do you approve manually?
rsgm an hour ago
I'll verify the PR code myself before merging, but that's usually a quick skim.