8

Hi all,

Decided I want to give Hermes a try, but man their documentation is horrid. So, for running fully offline, here's their "guide": https://hermes-agent.ai/how-to/run-hermes-offline

Now since that's trash, anyone here actually doing this? Did you just remove all references to non-local providers in the config.yaml? Are you using other containers for TTS and STT? Any help would be appreciated as I dive in.

Thanks in advance.

you are viewing a single comment's thread
view the rest of the comments
[-] Fmstrat@lemmy.world 1 points 3 days ago

Yea, connecting to my local llama instance was pretty straight forward. But then I realized there are still moe providers set up with openai and anthropic outside of the main providers, and then there are MCP tools and skills that don't ask permission to use the internet, etc. Just seems like OpenWebUI gives you a lot more visibility and control.

[-] pech@lemmy.world 3 points 3 days ago

Yeah I kind of got tired trying to manage all the changes the devs made to the harness, though the docs are explicit in saying nixos is a tier 2 platform lol.

I've been using deepseek-harness for a few weeks and it's been awesome

this post was submitted on 11 Nov 2026
8 points (70.0% liked)

LocalLLaMA

5662 readers
270 users here now

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

founded 3 years ago
MODERATORS