hey hn! i'm ben, co-founder and cto of raindrop. very excited to see our first oss launch here.
a little context for why we built this:
we were building agents internally, and we all got very tired of waiting to see traces show up in the cloud. i remember one specific moment, i was looking at my app locally, seeing every token streaming in, and thinking... what if my debugger showed every token too?
why does anything need to be sent to the cloud (ours, or anyone else's!) to debug an agent locally?
the more people we talked to, the more we realized everyone had the same exact problem. local agent debugging was non-existent. people couldn't see their traces, and their coding agents (e.g. claude code) couldn't either.
and so that's what we built.
i'd love to know what we could be doing better. there's some more info re: workshop here: www.raindrop.ai/workshop
I’ve been using this local debugger for the last ~week.
Seeing traces in real-time (and Claude seeing them too) is so so good. The velocity speed up is hard to understate.
Request for the Raindrop team: I wish your eval support was better. It’s not great having it completely disconnected from my CI system.
hey hn! i'm ben, co-founder and cto of raindrop. very excited to see our first oss launch here.
a little context for why we built this:
we were building agents internally, and we all got very tired of waiting to see traces show up in the cloud. i remember one specific moment, i was looking at my app locally, seeing every token streaming in, and thinking... what if my debugger showed every token too?
why does anything need to be sent to the cloud (ours, or anyone else's!) to debug an agent locally?
the more people we talked to, the more we realized everyone had the same exact problem. local agent debugging was non-existent. people couldn't see their traces, and their coding agents (e.g. claude code) couldn't either.
and so that's what we built.
i'd love to know what we could be doing better. there's some more info re: workshop here: www.raindrop.ai/workshop
also we're hiring :)
How does this feel different from Vercel AI SDK's newer local debugger? Richer in general?
hey! are you talking about ai-sdk dev tools? https://ai-sdk-tools.dev/devtools or something else i'm missing.
if so, few big differences:
* it can connect to your coding agent (e.g. claude code) so it can see traces, write evals, run your agent, etc.
* compatible with pretty much any sdk you can imagine (and growing - we just took a pr someone made for livekit support)
* dev tools is cool but more like a little widget in your browser. this is, imo, better agent trace viewer than anything that exists.
tldr; lots of perks to being an actual server/app on localhost
I'm really excited about this. Looks really handy and well designed.
hamel! we're big fans :) thanks for the kind words