jmulla
Re:It's Time to Reinvent Software Tickets for the AI Era
on Monday November 16, 2026 @09:07AM (#50517731)
And I agree this goes well beyond agents. This is a step towards capturing decisions in a shared form that's accessible to both humans and agents, while making those decisions easy to discover and retrieve when they become relevant.
Agents just make the need more urgent, given the speed and scale at which they operate.
Re:Show HN: Backtest a futures strategy described in plain English
on Monday June 29, 2026 @12:02PM (#48721016)
For HN I put up a no-signup sandbox at askfutures.com/hn you can run real backtests there without an account, so you can poke at it.
Show HN: Backtest a futures strategy described in plain English
Re:Show HN: Teemux – Zero-config log multiplexer with built-in MCP server
on Saturday January 24, 2026 @08:45AM (#46743460)
love the utility. I've used hacky stuff in the past to combine logs from different processes.
Can I aggregate logs from processes running on different machines?
Re:Show HN: Building Memory as a Service with Memrun
on Friday January 23, 2026 @02:41PM (#46736848)
Thank you for your interest! That's a great question, and I'd love to give you a thoughtful comparison. Could you share which memory and context services you've been looking at or are most familiar with?
Show HN: Building Memory as a Service with Memrun
https://www.autoencoders.com/papers/building-memory-as-a-service/
Python SDK for services where the expensive part is loading data, not processing it. Sticky routing keeps requests on the same worker, NVMe cache eliminates repeated S3 fetches, and you deploy with a decorator + one CLI command.