<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: sebastienburel</title><link>https://news.ycombinator.com/user?id=sebastienburel</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 08 Sep 2026 15:38:15 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=sebastienburel" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by sebastienburel in "Launch HN: Almanac (YC S26) – AI that knows your company"]]></title><description><![CDATA[
<p>The hard part for an always-on company agent is what survives a restart. My runtime snapshots the whole JS heap to bytes and restores it in a fresh process, so conversation and working state come back with no serialization code — but timers don't survive, so an agent re-arms them from declarative state after restore. How do you handle that? Is a long-lived agent's state checkpointed, or rebuilt by replaying context on each wake?</p>
]]></description><pubDate>Tue, 01 Sep 2026 08:48:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=49519569</link><dc:creator>sebastienburel</dc:creator><comments>https://news.ycombinator.com/item?id=49519569</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49519569</guid></item></channel></rss>