What harness are you all using? OpenCode?

I have a harness for my harnesses now. My Hermes manages Codex, CC or Cursor now and interact with me via Slack and PRs on GitHub.

It's nice because I can keep going from anywhere, other team members can see and interject in my Slack threads, and Hermes auto updates its skills with any adjustments that we make so we don't have to ask twice.

▲

mr_mitm 7 hours ago | parent | prev | next [-]

I found Claude Code to work best. You can use it with any compatible API.

▲

schaefer 7 hours ago | parent | prev | next [-]

Pi.dev at home.

And I’m slowly writing my own. But it’s garbage at the moment.

▲

pizlonator 4 hours ago | parent | next [-]

I wrote one and kept iterating by using it to fix bugs in itself

I still also use other harnesses, but mine is already at the point where I prefer it more often than not

You should totally keep working on yours. It’s a cool learning experience. And you might stumble on some good ideas that nobody else has had

▲

ylrd91 6 hours ago | parent | prev | next [-]

Don’t write your own. Fork maki.sh and customize it like I did. It’s built in Rust and is absolutely amazing.

	▲	schaefer 5 hours ago \| parent [-]
		Thanks for the suggestion, but that’s not a fit for me. I’m writing my own harness to learn. And I’m writing it in zig. But, I’ll absolutely add maki.sh to my reading list. So, that’s a win.

▲

leereeves 7 hours ago | parent | prev [-]

What kind of hardware do you need to run a useful LLM at home? To train one?

▲

schaefer 6 hours ago | parent | next [-]

> "What kind of hardware... "

At home, I mostly use openrouter.

A few bucks will realistically last you forever. I also bought a DGX Spark at launch. I've learned a ton. but it's not usually my daily driver. I do run overnight tasks on it, like "read this book and write up notes on each chapter..."

In retrospect, given the dirt cheap prices of apis and or renting hardware, buying hardware for inference was likely a mistake (but not enough of a mistake to sell it now).

	▲	margalabargala 3 hours ago \| parent [-]
		There are a lot of tasks I have, e.g. integration with homeassistant, that I absolutely will not trust a cloud provider for. On prem or nothing. I'm not willing to spend thousands for those features, so my house will remain dumber than it could be until prices come down in a year or two.

▲

CamperBob2 36 minutes ago | parent | prev | next [-]

Take a look at the docs for https://github.com/niko1221/strata for some ideas, particularly https://github.com/Niko1221/Strata/blob/main/docs/MODELS.md#... .

▲

mynegation 6 hours ago | parent | prev [-]

Schaefer says they write their own harness, not necessarily training or running a local model.

▲

minimaxir 6 hours ago | parent | prev | next [-]

For me, I used Zed Agent with Codex as it has native integration with Zed's ACP so it's pretty convenient.

However, Anthropic is pickier about the harnesses you can use with Claude Code and I noticed discrepancies when using Zed's External Agent feature with Claude Code, so I just use the Claude app. It's fine.

▲

smlx 4 hours ago | parent | prev | next [-]

Crush is great and easy to hack on: https://github.com/charmbracelet/crush

▲

denkmoon 7 hours ago | parent | prev | next [-]

Personally I've found Zed's agent to be much superior to OpenCode. IDK why but it gets better results from the same model on the same task. Using with GLM 5.3 and DeepSeek 4.1.

▲

hgoel 6 hours ago | parent | prev [-]

I've been pretty satisfied with OpenCode 2