Skip to content
Momentum Labs

Assistant models.
One step ahead.

We’re building smaller, cheaper models that finish tasks quickly, know the person and reuse what works.

Request model access

Our thesis

Assistant judgment belongs in the model.

A capable assistant should take less supervision and less work to build.

Fast execution

Less back-and-forth. More getting things done.

Repeating context and directing every step turns getting help into another job.

Our goal: find the relevant information quickly, connect it to the request and move the task forward.

Request + Connected sourcesReady to act

Personal judgment

Know the person. Anticipate what matters.

Remembering a fact means little if it never changes the next decision.

Use preferences, past decisions and current context to anticipate needs, with judgment about what matters, when to interrupt and when to ask.

Memory + Current contextA better next step

Reliable tool use

Know when the tool got it wrong.

A successful tool call can still return the wrong result. Someone has to notice.

Choose the right tool, check the answer and recover from mistakes. The aim is a correct outcome with fewer corrections from you.

Tool result + CheckVerified outcome

Learning through memory

Keep what worked. Stop repeating what didn’t.

Every task shouldn’t start from scratch. Every correction shouldn’t need repeating.

Our first focus is remembering corrections and reusing successful workflows. The goal: faster, more personal help as experience carries forward.

Corrections + What workedBetter next time

Research objectives illustrated above. Not live model demonstrations.

The direction

Better help. Less overhead.

More judgment in the model.

Teams should spend less time scripting every step. We want the model to carry more of the work: noticing what needs doing, acting and knowing when to ask.

Affordable enough to stay available.

Personal help should be available to everyone. Our goal is small models cheap enough to run all day, and eventually on your own device.

Longer-term research Lightweight model updates shaped by personal memory and preferences. Related research ↗

Personal help, for everyone.

Build your assistant
with our models.

For teams building personal assistants. Request early model access.