All activity
Yonas Biniamleft a comment
I built Solaris because most AI memory feels either fuzzy, forgetful, or impossible to inspect. Solaris takes a different path: keep the archive, derive structure cautiously, remember selectively through editorial review, and make divergence between current belief and historical record visible instead of hiding it. It’s open source, early, and meant for builders working on long-lived agents,...
SolarisArchive what happened. Believe. Know the difference.
Solaris is long-term AI memory built for honesty, not just recall. It keeps an append-only archive as source truth, derives structured memory cautiously, and uses editorial review to decide what becomes enduring memory. It also surfaces divergence between current belief and historical record, supports graph-aware retrieval, and can run in shadow mode beside an existing system before becoming authoritative.
SolarisArchive what happened. Believe. Know the difference.
Yonas Biniamstarted a discussion
<p>Hey everyone 👋</p>
Hey everyone 👋 I’m Jonas, an engineer with a background in quality and process optimization who’s now deep into AI and machine learning. Lately I’ve been building something that uses both to make experimentation a bit smarter; cutting down the trial-and-error and helping ideas move faster from concept to result. Curious to hear how you’re using AI or ML in your own projects, has it changed the...