YHK - yet another hacker news clone

Octomind – open-source AI harness that saves your tokens, static rust

31 points donk8r 1 hour ago 29 comments

tamimio 1 hour ago | parent

I will try it, but please, make the installation through package managers (linux), these curl scripts aren’t secure.

donk8r 1 hour ago | parent

Thanks for suggestion! Will do. Can I know which distribution are you using? Feel free to leave feedback after you try. Cheers

hackernudes 59 minutes ago | parent

I would vote against package managers. It just doesn't make sense to try to support them across Linux distributions.

If it's really static rust then either make it one binary. If that's not reasonable then make the release relocatable to run from any path. Also it should be simple and easy to run out of the source repo.

donk8r 56 minutes ago | parent

I think packgae manager still can be as an option. But for sure static binary should stay as is

CBLT 49 minutes ago | parent

I highly recommend just using `mise` with the cargo backend[0]. I use mise to manage all the harnesses I try.

[0] https://mise.jdx.dev/dev-tools/backends/cargo.html

donk8r 45 minutes ago | parent

interesting, never heard about it. How its better then just cargo install?

CBLT 32 minutes ago | parent

If you're installing just one thing, nothing.

octomind 48 minutes ago | parent

nice name

donk8r 47 minutes ago | parent

I like yours too! Perfect fit

jszymborski 42 minutes ago | parent

I'd like to see this benched against oh-my-pi because I've really been digging how it does compaction / snapshotting.

donk8r 40 minutes ago | parent

great idea. Currently working on updating benches on frontiers models, so far on glm-5.3 it's already showed great results. Can I have a link to oh-my-pi to make sure will sure use right one for it?

jszymborski 6 minutes ago | parent

https://omp.sh/

jakswa 33 minutes ago | parent

did they stick with the image-based compaction (when vision is supported i guess)? It boggled my mind: "snapcompact, which archives older history into dense images for a vision-capable model"

jszymborski 3 minutes ago | parent

it's in the docs! never have used it though https://omp.sh/docs/compaction

unsloppable 37 minutes ago | parent

Can someone save me a click? Does this improve quality or worsen it?

Tokens are cheap. Quality is what matters.

donk8r 34 minutes ago | parent

Our benchmarks shows that it best solver. Solves more than Claude on Opus while using glm 5.3, but still benching new models with most recent version.

The point here it has flexibilty in config, supervisors, automatic learning and also utilizeing jev-like models to gain maximum of efficiency while keeping solving rate intact

the_duke 30 minutes ago | parent

The README is AI slop ... is there anything actually special about this?

The feature list doesn't seem to show why it is significant compared to all the other harnesses.

donk8r 27 minutes ago | parent

Well it's beating Claude while using GLM-5.3 in solving the UNSEEN issues from real github PRs on our benches.

Yes, readme maybe sloppy, I'm using it daily along with claude and can say it works much better, but still personal opinion

You will never know if you not try, sloppy readme cannot say the product is bad IMO, but its your choice.

Thank for feedback. I will definitely will look and work on readme. But advise what exactly sloppy – would be much more valuable

james2doyle 11 minutes ago | parent

glm-5.2*

donk8r 4 minutes ago | parent

We benched it also on glm-5.3 not published. To be honest they act almost the same did not see any significant difference, while other benches show a lot

mtrovo 26 minutes ago | parent

From what I can tell this is a harness optimized to be used as headless background jobs, think about CICD jobs, or bugs auto triage. Instead of interactive HITL approvals you supply a policy file with the tools and commands you allow it to execute. Kind of cool idea, similar to pi but seems more specialized to dev cycle triggers.

donk8r 23 minutes ago | parent

Yes. Kind of right. No TUI but still old CLI approach that some of us still love. It can be used interactively and I use it daily, but so far it's optimized for autonomous work at max and so far finalizing task while running in isolated environments (we use docker for that)

Murfalo 24 minutes ago | parent

Holy tagline. "The CLI-first AI coding agent runtime. Pipe it, schedule it, embed it. One binary, any model, MCP-native — built for autonomous work, not just chat."

I feel like I'm taking crazy pills...

donk8r 22 minutes ago | parent

Blessed by compiler. Sometimes one of those crazy pills take you out of matrix :)

weego 19 minutes ago | parent

I don't know if I want any of those things. Can I still just throw it my csvs and make it do my data science work for the day so it doesn't distract me from baldurs gate?

buster 20 minutes ago | parent

Why would i choose that over maki.sh? A comparison to maki would be great!

donk8r 19 minutes ago | parent

Hey. Never heard about it, but I will take a look. thanks

james2doyle 11 minutes ago | parent

Compare against ante as well: https://ante.run/