Anybody else feel like goose is really powerful and interesting but also it’s not at all clear how to use it? cc nostr:npub1sg6plzptd64u62a878hep2kev88swjh3tw00gjsfl8f237lmu63q0uf63m

https://block.github.io/goose/

Reply to this note

Please Login to reply.

Discussion

Yeah.

Based on my extremely brief look at it, it looks like an application that I kind of already use called JAN that helps you run local models. I think the leg up that this one has is the whole agent's thing, which I'm still not 100% sure how those work.

took me a bit and then it clicked. you connect MCP tools which are stdio jsonrpc servers. they provide a tools/list endpoint which goose loads into the ai prompts so that they know what to do.

there's not much more to it, goose also provides ways to connect to different ai backends.

enabling the developer mcp is most useful, since it gives ais access to your shell

Yeah, i’m muddling through it… i wasn’t familiar with MCP and i think there’s a few things you need to do in setting up goose to make it actually work well.. Documentation and improve tooling will help. My suspicion is that the goose developers are so embedded in their world that they can’t see what others need to do to get started.

here’s a cli I was using before Goose showed up. same ux but a little more obvious how it plugs together.

https://github.com/mark3labs/mcphost

can it also control the shell inside a container? would be cool to tell the ai to quickly spin up a container with some software and then let it work with that

neeerrrrddddddd

😱

I have not check goose 🪿

I always wanted to have emoji bitcoin on my keyboard ..

now you have to contribute to make it more intuitive haha

Hi hi hi

Why is cancelled

Could you see my dm?