Patt_

not sure what u mean, but if u are making the tools for your agents, no. if u are using other third-party tools that're not free, and u tell the agent such tools cost money per call in the schema, i'd say a good model will avoide it unless u push it in the prompt.

It's all over Chinese Taobao. biggest catch would be that all of the sutff is in Chinese, they have an international version in english but if you run into issues and have to talk to the seller, 99% of them don't speak Chinese but with AI translation that won't be a problem. you can even get Claude Code shared plan there as well, what they do is to buy the MAX plan and then have a couple people sharing it, which on average still beats your $20 Pro plan's allowance.

You can also add Google’s AntiGravity into the bunch. They have free allowances of Claude and Gemini 3.1 Pro there ready right after install & login. & you can also get cheap Google AI Pro shared plans there as well, just to get higher allowance on all these models.

There are many ways to get around the session limit, gotta be creative. Update: Windsurf has just made a shitty move by changing their pricing structure from credits to rolling window percentages, not sure if it's better or worse, free models are still there & I haven't hit any rate limit so far.

Hey man, here's how to properly spend your 50 bucks and get the most bang for the $$:

opencode go - $10 a month gets you decent allowance with latest GLM, MiniMax, and Kimi. Windsurf - $20 gives u access to nearlly all models.

For me, I'm having these two subscriptions plus: shared Codex plans & shared Kimi coding Allegretto from Chinese resellers for around $10.

I only use the Claude Opus/Sonnet inside Windsurf after everything is crystal clear, or I want to let it handle tricky stuff where other models can't address. I use GLM/Kimi for everything else. And Windsurf offers free models all the time.

Interesting project. The doc pages look solid and well prepped. So if you register your agents and publish to the marketplace, how is decision-making (paying u to use your agent) done? Automatically by the agent or agent owner?

yep to all points, and for an AI to be able to do this level of background check as a real human being, you need more than just simple prompts & basic wrapper-level tools. & as long as sloppy ai-made emails still get results, nobody cares enough to pour more effort & tokens into them.

Whoa, So Sam and Drio are just gonna buy out every popular open source projects now?

thanks for sharing and congrats. solid stuff! I would add that expect tripple the amount of applying and ghosting if you are mid-level.

Gotta optimize your spendings, and from my own ex you can get the same desired quality for all your current needs.

Don't subscribe to Claude or GPT-4 or Gemini. Instead, go get something like Perplexity or similar tools so that you can have access to all these latest premium AIs (300~600 queries/day) If you're comfortable with copy-pasting back and forth, this one thing meets all your needs.

And on the IDE side, subscribe to only one IDE, And even with IDEs, you can cut down costs, like going for qoder(just came out, free 2 week trial) or Trae (3 bucks a month, you can get that deal ). As for Claude Code, swap in qwen or DeepSeek apis. They're compatible with Claude Code and works ootd.

Unless these AI bots choose to pass query data in these UTM parameters, i'd say there's no way to obtain such information, except for you to go into an ai and try to trigger the ai pulling searches that contains your website urls.

just close it

Cool idea, worth continuing if you automate data refresh cheaply.