Manifesto

Idle capital,
active inference.

For most of computing's history, the scarce resource was storage, then compute, then bandwidth. None of those are scarce anymore. What is scarce — what will stay scarce — is the right to run intelligence.

Inference is becoming the most important commodity of the next decade. We are early to it being priced as one.

DIEM

Venice was the first to tokenise this. One DIEM gives its holder one dollar a day of API credit on top-tier models. The credit is daily — what isn't used within twenty-four hours is gone.

Most DIEM holders don't use their full daily allowance. Some use a fraction. Some use none. The remainder evaporates.

That's the gap cache. lives in.

What cache. does today

cache. is a vault. You deposit DIEM. The vault stakes it on Venice and resells the daily inference credit on inference marketplaces — Surplus Intelligence first, others as the ecosystem grows. The USDC earned is swapped back into DIEM. Your share of the vault, vDIEM, claims its slice of the underlying.

Put your inference to work.

Think of it as an index fund for inference. You don't pick which model, which marketplace, which buyer, or which moment to sell into. You hold one position; the vault does the unglamorous work of putting otherwise-idle daily credit to work and compounding the proceeds back into the underlying. Simplicity at the front, machinery at the back.

No leverage. No emissions token. No vote-locked governance theatre. The vault holds your DIEM staked on the public Venice contract; it has no power to drain you; it has no admin escape hatch.

The vault layer — and only the vault layer

There are three layers to this market: the marketplaces where inference is bought and sold, the buyers who consume it, and the vault that pools capital, manages selling, and compounds. cache. is the vault layer. We sell our credit through neutral marketplaces — we never become one, and we never run a buyer-side router across them.

This is a deliberate line. A protocol that holds inventory and operates the market it sells into has asymmetric extraction power over its own users — and users feel that conflict before they can name it. The infrastructure that survives stays a pure layer. So cache. stays put: a customer of neutral markets, never their operator.

Yields are not guaranteed. They reflect actual inference demand on the day, less operating costs. If demand falls, returns fall — we will not paper over that with emissions.

What cache. might become

Compounding a single user's DIEM is the first step, not the destination.

The longer-horizon idea is Protocol-Owned Inference: a protocol that quietly accumulates tokenised inference over years rather than scrambling for it under pressure. Other protocols spent a cycle buying their own liquidity. We're interested in applying the same instinct to a scarcer commodity.

The mechanism is a flywheel — the Hudson Yards kind, where the revenue a development throws off pays for the infrastructure that makes the development more valuable, which throws off more revenue: the vault resells inference and earns; surplus beyond operating costs buys more DIEM; more DIEM means more daily credit to resell; which earns more. Each turn makes the next one larger — and none of it depends on a token price doing anything in particular.

We don't know exactly what the end state looks like yet. We will design it in public, ship in increments, and not pretend the mechanism is fixed before it is.

Phases

Now
The vault
ERC-4626 on Base. Deposit DIEM, the vault stakes it on Venice and resells the daily inference allowance on inference marketplaces. USDC harvested is swapped back into DIEM. Conservative deposit cap, no emissions, no admin escape hatch.
Direction
Surplus, redirected
If the vault is sustainably profitable beyond operating costs, the surplus may be directed toward longer-horizon positions in tokenised inference. The shape of that — what we hold, how we hold it, who decides — is open. We will show our work as we go.
Endgame
Protocol-Owned Inference
Cache may evolve into a protocol that quietly accumulates inference exposure over years, on the bet that priced-by-the-token compute is the most important commodity of the next decade. This is a direction, not a guarantee. Anything beyond the vault you see today is experimental.

What this is not

What we owe you

If you can't read the contract, don't deposit.

If you want to deposit: withdrawals are batched daily and Venice imposes a 24-hour unstake cooldown. Expect 1–2 days from request to claim.


A cache for what comes next.
cache