HackerTrans
TopNewTrendsCommentsPastAskShowJobs

nicklo

no profile record

Submissions

Show HN: Ash – OSS Infra for Running Claude Agent SDK

github.com
1 points·by nicklo·vor 4 Monaten·2 comments

comments

nicklo
·vor 2 Monaten·discuss
Cortisol spit curve tests are pretty cheap, so I was disappointed to see the title claim not substantiated with real data. Consider biometric testing next time you distribute!
nicklo
·vor 3 Monaten·discuss
or say yes? decel mentality like this is why europe is falling behind. some poor startup will try to backfill these contracts to be the new palantir of europe only to be cut at the knees by regulation and more outcry think piece boycotts like this. rinse and repeat until the us and china become the only relevant acceleration hubs on earth during the singularity
nicklo
·vor 4 Monaten·discuss
the animation of the model name text when opening the detail view is so smooth and delightful
nicklo
·vor 4 Monaten·discuss
Congrats on launch! As the agent cli’s and sdk’s were built for local use, there’s a ton of this infra work to run these agents in production. Genuinely excited for this space to mature.

I have been building an OSS self-hostable agent infra suite at https://ash-cloud.ai

Happy to trade notes sometime!
nicklo
·vor 4 Monaten·discuss
Yeah with sandbox pre-warming and disk co-location its fast enough to avoid UX cold start penalty.

On write amplification — we persist at the message level, not per SSE chunk. The sandbox's workspace filesystem (claude code's native jsonl files) is the source of truth for resume, and the DB is for queryability, tracing, etc - so fire and forget works fine here.
nicklo
·vor 4 Monaten·discuss
I’m building a self-hostable, open source agent sandbox orchestrator here: https://github.com/ash-ai-org/ash-ai
nicklo
·vor 5 Monaten·discuss
directionally correct but important to note the water wasted by sustaining the insufferable human is much higher than producing the tokens
nicklo
·vor 6 Monaten·discuss
i've always wondered (for this, portkey, etc) - why not have a parallel option that fires an extra request instead of mitm the llm call?