Kelex: Agent memory without writing it yourself

Most agent frameworks treat every run like a fresh chat. No real memory. No progressive flagging when the agent isn't sure. No tenant model. Builders who want a real long-running agent — one that remembers the user across months, picks up where it left off, and flags what it can't decide — end up writing the substrate themselves.

Kelex is that substrate, productized. Typed memory. Tenants and agents as first-class objects. Bounded confidence with progressive flagging. Webhooks for human-in-the-loop steering.

We use it to run Lara and the BFTS content stack ourselves before selling it.

Why this matters for us:
https://brownforces.io/solutions