yangshi07

I am working on https://github.com/fastagent-sh/fastagent

Which let me deploy pi-durable agents to AWS, Cloudflare, Fly.io as services with every cheap cost(in MicroVM)

What I assume that the agents should run as a "Web Service" on the cloud and do the work silently and complete the work without the chat. We don't chat with our system monitoring, don't chat with log system.

This is possible. Open source model is very important for the whole industry.

I believe is not a good idea for the model providers provides a Agent Infrastructure or hosting service.

This area should be open source and supported by the cloud providers. Because I don't really want to be locked to a model provider when I am building my agents.

Actually this is happening, I found couples:

- https://flueframework.com from Astra - https://eve.dev from Vercel - https://fastagent.sh looks more independent, cloud neutral

There should be more and more options, the OpenAI Agent API may be another GPTs

But it is really hard to remember the shortcuts

After you point this out, it is obviously right!

So glad to see someone working on making fucking coding better — making LLMs write good code, not just vibe and wow, and not just pretend the code is magic.