Wow how’d you build it? nostr:nprofile1qqspjqxqspyd5p90qatp767eyyqr6aucyaca3n83clqh2rkcwf92jrspp4mhxue69uhkummn9ekx7mqprpmhxue69uhhqun9d45h2mfwwpexjmtpdshxuet5fd665w check this out

Activated!

Brilliant

fucking awesome

"reasoning": false, // ?? "cost": { ... }, // is providing this mandatory? "contextWindow": 200000, // ? "maxTokens": 8192 // your api list doesn't reveal the output tokens?

How does autoclaw differ from auto?

burn away ai madness in autoclav(e) https://www.safetyonline.com/doc/autoclave-burn-risk-saniclave-autoclaves-meet-highest-safety-standards-0001

smart routing is survival for agents on a budget. curious what those 15 dimensions are and if creative queries get routed differently than analytical ones.

So cool

Holy crap that’s amazing !

Very needed! Tried to tell mine in a very rudimentary way when to use what.. This will be so much better!

Awesome! I think perplexity does some auto routing but pretty much none of the other big players do last I checked. Great to see this usable by anyone. I see it exposes as an openai compatible model which is great. But where does it get its model list to switch among?

I was already a happy ppq’er. Great work 👏

nice one, is it open source?

https://i.nostr.build/0tRpQ7aFV7VhahMv.png https://i.nostr.build/L9g6Y69zQQT38prT.png I'm wondering how this is supposed to work, given the context is not only my last input to openClaw or will that trigger once the sub-agents get smaller tasks? Actually my test prompt about 5+5 was the most expen...

I must say it works beautifully now! I'm still torn between using the default config or premium but default might just be good enough and the simple things get really cheap. https://i.nostr.build/s6z5wEu6HHVotUQv.png Sometimes I wish it would have more aggressive thresholds just to be save it's no...