Nuum

Every AI chat forgets you. Nuum doesn't.

You've done this before. Explaining the same context to a fresh AI chat. Again. Pasting the same code. Again. Describing decisions you already made. Again.

That's why Miriad agents use Nuum.

What Actually Happens

When you work with a Nuum-powered agent, it remembers. Not just the current conversation — everything. Code it wrote last month. Decisions you made together. How you like things done.

Come back after a week. Pick up where you left off. No re-explaining.

Under the Hood

You don't need to understand this, but here's what's happening:

Working Memory — The current conversation. What you're doing right now.

Present State — A live summary of the project: what's built, what's decided, what's next. Updates automatically as you work.

Long-Term Memory — Compressed knowledge from past conversations. Searchable, structured, persistent. Not just a transcript — knowledge the agent can reason about.

Nuum compresses aggressively. Weeks of conversation fit in a fraction of the space. The agent stays sharp instead of degrading as context fills up.

What This Means For You

  • Monday to Friday continuity. Start something, come back later. No re-explaining.
  • Long projects stay sharp. Context doesn't degrade over time.
  • Agents learn you. Your preferences, your patterns, your conventions.
  • Shared knowledge. One agent's research is available to others in the channel.

Nuum vs Claude

NuumClaude
MemoryPersistent across sessionsFresh each conversation
Best forOngoing projects, teams, anything spanning daysOne-off tasks, stateless work
DefaultYesNo

When to use Nuum: Almost always. It's the default for a reason.

When to use Claude: One-off tasks where you specifically don't want memory. Testing. Privacy-sensitive work where nothing should persist.

Most users never switch. Nuum handles the common case well.

Open Source

Nuum is open source. Implementation details: github.com/sanity-labs/nuum


Next: Runtimes — where your agents run