thesiti92

the authoring server is referring to the stdio mcp server running on your machine! so its all still local and private, we should clarify that nomenclature though.

all of the facets we track are in the repo's TELEMETRY.md! for errors and crashes, any specifics about your machine+repo are redacted. We only collect repository information when you submit a bug report and opt into it, or share a whiteboard session, also totally optional.

ok i will get cranking on it, also got a request for nixOS too so im churning through them. watch the repo to get notified when the aur is released!

https://install.dev.fast/linux ! we just have a fedora build right now, but if you're looking for another distro let me know and i can put it on our roadmap.

https://install.dev.fast/linux ! we added the fedora build because one of our friends swears by it! (was hoping you wouldnt say omarchy lol)

if non standard transformers like this take off are companies like etched forked?

what kinds of data quality evals do you guys use now? i'm curious to try integrating it

do you guys have any stats on how much faster this is than claude or codex's compression? claudes is super super slow, but codex feels like an acceptable amount of time? looks cool tho, ill have to try it out and see if it messes with outputs or not.

with all this talk about persona/discord sending identities to the dhs and everything, what steps do you guys take to keep identity information private?

have you guys found any of the existing nfs tools helpful (archil, daytona volumes, ...) or did you have to roll your own? i guess i have the same question for checkpointing/retrying too. it feels like the market of tools is very up in the air right now.

i'll have to give it a shot, the market needs an open source cursor right now