pancomplex

Not yet, but that sounds like a useful overview to add to the landing page!

It will automatically pick the best one for your HW on install

Sorry about that. I’ll make sure it cleans up after itself in the next update. What was the main issue you ran into?

I went back and forth with my coworkers on the naming and we essentially voted on Hob vs Garth. Vote came to Hob. Do you prefer Garth?

So basically allow you to point the LLM to a hosted model on your local network if I understand correctly?

thank you! Haha I always make it a point these days do handwrite these things. I think everyone is tired of overly verbose perfectly written AI text.

Thank you. Yes please fork that's exactly why I put it out on MIT license :)

Here's roughly what it picks today from my testing:

- 8 GB Mac (M1/M2): Gemma 4 E2B

- 16 to 18 GB Mac: Gemma 4 E4B

- 24 to 64 GB Mac: Gemma 4 26B A4B

- 128 GB Mac Studio: gpt-oss 120B

- Windows/Linux with an RTX 3060 or 4070 (12 GB) and 32 GB RAM: Gemma 4 26B, split between the GPU and system memory

- RTX 4090: Gemma 4 26B fully on the GPU

- No GPU, 16 GB RAM: a compressed Gemma 4 E4B on the CPU

High level, it looks at your memory and memory bandwidth and then picks the smartest one that stays above about 15 tokens a second with room for a decent context.

It's still pretty tricky to do this as a solo dev to keep feature parity in my experience (fun fact, even Claude's own Desktop app is made in Electron).

That being said, majority of the heavy LLM lifting happens natively with llama.cpp :)

Good call. Are you on PC/Mac/Linux?

Thank you! Would love to hear which ones you've used. Working with local files without anything going to the cloud was the main thing I wanted. I tried Jan, OpenWork, Chatbox and Lobe, and couldn't get that working well in any of them. If there's one I missed it would be great to check it out!!

Thank you! It finished the full game!

Are you ok bro?

The next version I make should take advice like this from the chat

It has continued to surprise me throughout all of this so hopefully it will again

It has the option to go back and level up its pokemons + switch it up. Hopefully it gets the same idea as you soon!

I wrote down a series of 33 high level goals + some sub goals for completing the game

Fair point, but I’d challenge anyone to build an ai or hard coded engine that, even following a walkthrough, completes the entire game for under $2 in tokens

Thank you. What I realized is that Jev is incredibly powerful for the decision making part of it when presented with a scenario that gives it a little context. It looks like we’re gonna be able to beat this game for under $2 of tokens. This is what blows my mind

The more the merrier!

I challenge you to fork the repo and solve it faster using less tokens/cost than Jev :)

This runs entirely on Jev as the only AI with a typescript harness that feeds it selective context.

Thank you! And interesting data point on Fable burning out on tokens so early.

Nothing fake here and fully open source if you wanna take a peek. It does make a bunch of mistakes, often. But it eventually recovers!

https://github.com/christianmat/jev-pokemon

Agreed this would be super cool and I do see that coming in the future. But Jev-level latency just isn't there yet with full images.

That was how I first implemented it. Jev sadly never left Pallet Town.

It's connected to the ROM of the actual game, so it can see a lot of things. It has multiple tools available, including being able to move to coordinates.

All in the OSS repo if you wanna play around with it: https://github.com/christianmat/jev-pokemon

I just took your advice and added it to the list of Jev decisions. Watch it name its next Pokemon!

it made it through!

Like others have mentioned in this post, I think a mix of models like Jev for simple stuff + a smarter reasoning model for more strategic thinking is the optimal solution. This experiment however is purely Jev. Which sometimes can be kinda dumb.