This is great feedback (thank you for taking the time), & you especially bring u...

echelon · 2026-07-15T07:18:33 1784099913

Can you explain what you're using the local compute for vs. the API-based frontier models? That was entirely unclear to me.

Are you running tool calls that include inference with local fine tunes? And fast math packages? Controlled by the frontier model agents?

Is there a way folks can contribute to this?

colin7snyder · 2026-07-15T10:08:21 1784110101

Thank you for the questions echelon.

1) As far as the AI models go, we used GPT 5.6 Sol, Fable 5, and Gemini-2-embeddings across the system

2) Yes, the agents are given bash tools that allows them to interact with the preinstalled mathematics packages/dependencies that are on the VMs

3) This was a setup as a relatively quick project without much thought for future contributions, I will spend some time thinking about how i could make it more open.

echelon · 2026-07-15T14:17:07 1784125027

This is so great!

I hate to bother with more questions, but I'm just so curious about this.

If you could roughly sketch out your agentic harness loop in a sentence or two, what does it look like? Which model(s) do the driving? How is progress measured?

What's your daily/monthly budget for this look like, if you don't mind my asking?

vessenes · 2026-07-15T11:32:28 1784115148

Keep it up! This is amazing work.

glitch-hunter · 2026-07-15T12:23:59 1784118239

I’ve been working on one problem for three weeks with fable if you want the repo