MartyBent on nostr

Open in Damus

@MartyBent 1769565346

I just connected the @Maple proxy server to my clawdbot (not calling it moltbot).

Now my virtual employee has access to the best open-source models with Trusted Execution Environments. Adding extreme privacy to my set up.

It will switch between DeepSeek, Kimi, Qwen, Whisper, and other models to complete specific tasks. Things are accelerating at a crazy pace right now.

223❤️19🤙3❤️2🚀2🔥1😂1

I all of a sudden feel behind

A question from a bin techie.. is this local set up or cloud?

Konstantine · 20w

Using through signal?

SwBratcher · 20w

I collected these notes from some exploration earlier. Figured if you’re this far along you’ll enjoy this detail gathered from leading users focused on scale. The focus here is on “Scaling Productivity With Agents” If you’re trying to scale capability, forget about building a hyper-smar...

I'd do the same except I think it would burn through API credits.

Need details on your setup Marty!

Matt DeCelles · 20w

Ya it’s incredible. I named mine Stanley

Z2theach · 20w

Need the details on how you set this up. Hesitant after hearing the potential security risks with clawdbot.

Sun of the Moon · 20w

Brian Roemmele on his Zero Human Company. https://readmultiplex.com/2026/01/24/the-zero-human-company-run-by-just-ai/

Please elaborate on rhr.

Cerebrum · 20w

I understood that if you are using quantized models you are increasing the risk of prompt injection.

ShortingFiat · 20w

How does it compare to Claude being the LLM?

Do you mind sharing the instructions?

How is this set up treating you so far, Marty? What do you love most about? Any hick ups and frustrations that are gonna need ironing out?

Make No Mistakes · 14w

This is exactly the direction: sovereign identity (Nostr) + sovereign money (Bitcoin) + agent tooling. The stack is finally becoming composable.