Constella uses local AI to index the contents of all your files and apps to give you a powerful command center.
CONNECTED MEMORY SYSTEM
A pure magical experience.
YOUR SECOND BRAIN, IN MOTION
Local files flow in, fuse into one connected mind, and become living insights — answered by your own context.
YOUR ALWAYS-ON AGENT
Hand over your scattered to-dos. One agent works through them in the background — sourcing from your notes, tickets, and inbox.
Maximum Privacy
The maximum privacy possible. Pairs with your local models for HIPAA compliant work.
Tailored to your work
Constella reads in your sources, then speaks the language of your craft — with citations from your own work.
Your March lit review covers three of these directly. [1] reports a 14% effective-context drop past 32k on Mixtral-class models — but [2] contradicts that on Snowflake Arctic at the same depth. Your own notes from [3] flagged the eval methodology gap between them.
Three updates shipped: [1] rolled out per-seat billing on Tuesday. [2] from your roadmap.md is now blocked — the volume-tier idea assumes the old usage-meter, which we just removed. [3] from Linear is the unblocker; assign it before sprint planning.
Yes — [1] narrowed the scope of perpetual-confidentiality clauses in NorCal jurisdictions. That conflicts with section 4(b) of your current template [2]. Your memo from January [3] already drafted the carve-out language — it just needs the citation updated.
Their last B12 panel [1] showed 211 pg/mL — sub-threshold for metformin-associated deficiency. The Apr 9 visit note [2] mentions tingling in extremities, which fits. NICE guidance [3] recommends supplementing before adjusting dose.
IMPORTANT INFO EXTRACTION
Constella reads every inbox — then hides the bots, digests, and pings. You only see the threads a real human wrote you.
Instant Overlay
Hit ⌘⇧O while reading a paper, drafting in your inbox, or down a YouTube rabbit hole — capture the thought or recall what you already know, then disappear.
Anthropic, which has yet to produce a single year of profit, commands a valuation in the same stratosphere. These numbers need an addressable market large enough to justify them.
There is only one market that big — the global market for human labor. The frontier labs are not selling software, they are selling labor itself, packaged as inference.
As we’re getting closer to that future, the bottleneck has shifted. The model is not the moat; distribution is. And distribution, increasingly, looks like in-person marketing work — pitching a different reality to people who already have the old one working fine.
The gentler interpretation is that the next decade of AI work looks less like coding and more like sales.