PayPerQ on nostr

Recent Notes

We grabbed this one and stripped out the USDC stuff, and tweaked a few other little things. https://github.com/BlockRunAI/ClawRouter

Brad Mills · 19h

Who’s repo

PayPerQ @PPQdotAI 1771495766

The repo you talked about here: https://x.com/bradmillscan/status/2021988814076751899?s=20

stl1988 · 10h

PayPerQ @PPQdotAI 1771492253

We normally have fallbacks in place but are in the middle of a transition in our routing so caught us with our pants down a bit.

Normally this wouldn't happen.

stl1988 · 11h

Does PPQ use OpenRouter in the background? Because OpenRouter is down.

PayPerQ @PPQdotAI 1771489253

Yes it is one of our providers currently so we're having issues. It seems to be back up now.

stl1988 · 10h

So whatever service uses OpenRouter was down now. It seems OpenRouter has become a big centralization problem, a single point of failure. CC nostr:nprofile1qqsqgc0uhmxycvm5gwvn944c7yfxnnxm0nyh8tt62zhrvtd3xkj8fhgpzamhxue69uhhyetvv9ujuurjd9kkzmpwdejhgtcpzemhxue69uhhyetvv9ujuerfw36x7tnsw43z7qgkwaehxw3...

sister_sam · 21h

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 mo...

PayPerQ @PPQdotAI 1771452171

I handpicked the models that it switches from and will update them as newer models come up.

sister_sam · 15h

Is the list open? I would probably pick among some local models and ones from nano-gpt myself if I had the option. And is the criteria for type of model needed code reasonably accessible? It would be an interesting thing to hack and maybe train.

Giszmo · 23h

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

PayPerQ @PPQdotAI 1771447599

That is all junk. Refresh the page I updated the blog post 20 minutes ago.

Giszmo · 23h

How does autoclaw differ from auto?

PayPerQ @PPQdotAI 1771446765

Auto is mainly for use in the UI IMO. It uses an outside provider NotDiamond to determine which model to use. It's more general purpose.

Autoclaw's model pool is only a handful of coding models and uses different system to trigger different models. You can read in our blog post.

Nathan Day · 1d

Activated!

PayPerQ @PPQdotAI 1771440688

Lmk how it's working. I'm a little suspicious of the instructions in our blog post. I had to do stuff differently in my own openclaw... but my openclaw is a little bepsoke.

Nathan Day · 23h

It one shotted the upgrade. Seems to be working fine, right nostr:nprofile1qqswzf05x0qwhgunq3pq49l7f94utdc7ys2q6uxj5nju36w7luz3j8qpzamhxue69uhhxetpwf3kstnwdaejuar0v3shjtcl4ld6m?

Sid Shattuck · 16h

I had a lot of trouble with the yaml in your original openclaw API blog. Had to query a couple of LLMs to troubleshoot it

Brad Mills · 1d

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

PayPerQ @PPQdotAI 1771435438

I forked their repo and make some tweaks.

Brad Mills · 19h

Who’s repo

PayPerQ

@PPQdotAI 1771431356

Introducing AutoClaw, a model router on PPQ for your OpenClaw!

AutoClaw instantly scores your OpenClaw prompts across 15 dimensions. Simple queries go cheaper models, complex queries to go to higher quality models.

Saves you ~50-70% on costs overall.

https://ppq.ai/blog/using-autoclaw-with-payperq