Why Cachee How It Works
Bitcoin Cache Layer Polygon zkEVM Cache Layer Solana Cache Layer
All Verticals Zero-Knowledge DEX Protocols Validators MEV RPC Providers
Pricing Documentation API Reference Blog Demos Start Free Trial
zkEVM proof verified → 99.6% hit rate STARK proof delivery < 5µs warm · vs 200ms re-verification cold Recursive proof composition cached 98% reuse rate Bridge replay verification eliminated → 8,200× speedup Post-quantum attestation 74 bytes · ML-DSA + FALCON + SLH-DSA Prover compute reduced 87% via cached intermediate state zkEVM proof verified → 99.6% hit rate STARK proof delivery < 5µs warm · vs 200ms re-verification cold Recursive proof composition cached 98% reuse rate Bridge replay verification eliminated → 8,200× speedup Post-quantum attestation 74 bytes · ML-DSA + FALCON + SLH-DSA Prover compute reduced 87% via cached intermediate state
AI Cache Infrastructure · Evidence-Backed Outcome Cache for Polygon zkEVM

Cache zkEVM Verification Once.
Reuse It Everywhere.

Cachee is AI-powered distributed cache infrastructure for Polygon zkEVM sequencers, provers, bridges, rollup-as-a-service stacks, and L2 indexers. Evidence-backed outcome caching eliminates duplicated STARK proof verification, cuts recursive composition cost, and removes bridge-message replay. Downstream systems independently verify the cached result without re-running the proof and without trusting the cache operator. H33-74 attaches a 74-byte post-quantum evidence reference to each cached proof outcome; H33's cryptographic replay reconstructs the trust path. Cachee stores and serves across the industry's migration to PQ-secure proof systems.

Live integrations: ← Bitcoin ● Polygon zkEVM Solana →

The H33-74 evidence element — not Cachee — lets independent parties trust each cached proof outcome without trusting the cache operator. That single property converts zkEVM verification from a per-system cost into a shared, portable asset — the foundation of distributed verification infrastructure.

— The category shift

The hidden cost

Why zkEVM verification is expensive — and why repeating it wastes compute

zkEVM proofs are designed to compress execution into something a verifier can check in milliseconds instead of milliseconds-per-transaction. That works — but "check in milliseconds" still gets paid millions of times across the modern zk ecosystem. Sequencers verify proofs before posting. Bridges re-verify on the destination chain. Rollup-as-a-service operators verify on customer infrastructure. Indexers re-verify on every reorg or schema migration. Exchanges re-verify before crediting deposits.

The waste is structural. A single STARK proof can be 200–500 KB. Its verification involves polynomial commitment checks, FRI queries, hash chains, and pairing operations that — while fast — are non-trivially expensive when paid per consumer per proof. Recursive composition compounds the problem: a proof of proofs still has to be verified by every downstream party.

The Polygon zkEVM protocol didn't pick a wasteful design. Modern zk infrastructure has scaled the cost of verification to the point where verification itself is the bottleneck. Every new consumer pays the full re-verification tax.

Modern zkEVM infrastructure wastes enormous compute
Re-verifying identical proofs across sequencers, bridges, indexers, exchanges, and analytics systems. Each proof gets checked dozens of times by parties that could share a verification result — if there were a portable, trustable receipt.
Large proofs are expensive to deliver
STARK proofs are hundreds of kilobytes. Pushing them to every consumer, every relay, every verifier multiplies bandwidth and latency. Cachee delivers the cached proof and a 74-byte attestation; the consumer verifies the attestation, not the full proof.
Recursive composition compounds the cost
Proof-of-proofs schemes (recursive STARKs, SNARKs over STARKs) do not eliminate downstream verification. Every aggregator still re-runs the verifier. Cachee caches the recursive intermediate and distributes it as a reusable verified result across composition layers — removing duplicate work at every aggregation step.
Operational economics

Where the duplicated zk compute actually lives

These are the operational line items zkEVM teams pay for every day. Each one collapses from per-consumer → per-attestation with portable verification receipts.

Prover compute
Provers regenerate intermediate witness data and partial proofs across batches. Cachee delivers cached attested intermediate state so the next prover starts from a verified baseline instead of cold.
On-chain verification gas
Smart-contract verifiers on L1 burn gas re-checking proofs that have already been verified off-chain by sequencers, bridges, and provers. Cachee distributes off-chain attested verification reused by lighter on-chain validation paths — eliminating duplicated proof verification across the on-chain/off-chain boundary.
Sequencer compute
Sequencers verify proofs from provers before posting batches. Centralized sequencers do this once; decentralized sequencer sets repeat the work N times. Cachee turns the first verification into a receipt every other sequencer can trust.
Bridge replay verification
Cross-chain bridges re-verify zkEVM state proofs on every destination chain. With Cachee, the first relay's verification is reused as a portable proof by every downstream chain — Bitcoin, Solana, and beyond. Per-relay verification compresses to per-proof.
Recursive aggregation cost
Proof aggregation services (proof markets, restaking-backed prover networks) re-verify each sub-proof during composition. Cachee caches aggregation-intermediate proofs across the aggregation graph — reducing recursive composition cost from quadratic re-verification to linear lookup.
Indexer / RPC replay
L2 indexers and RPC providers re-process zkEVM state on every restart or shard split. Cachee captures the replay result as a portable attested checkpoint — a new indexer boots from that checkpoint, never from genesis. Restart cost collapses to a single attestation verification.
Architecture

How portable zkEVM verification works

A single cached proof verification anchors the source of truth for every downstream verifier. The post-quantum attestation is what makes each cached outcome independently verifiable without trusting Cachee — the H33-74 evidence reference, not the cache, anchors trust — eliminating the per-verifier STARK re-execution tax.

01 / VERIFY ONCE
Verify once
Cachee runs the full zkEVM verifier — polynomial commitments, FRI queries, hash chains — on real Polygon zkEVM infrastructure.
02 / ATTEST PERMANENTLY
Attest permanently
The verification result is wrapped in a 74-byte H33-74 post-quantum attestation: ML-DSA + FALCON + SLH-DSA. Three independent hardness assumptions.
03 / REUSE EVERYWHERE
Reuse everywhere
Every downstream system — bridge, indexer, exchange, aggregator, restaking prover — reads the attested receipt and independently confirms it.
04 / ELIMINATE
Eliminate duplicated computation
Independent systems verify the attestation instead of re-running the STARK. The cost of "trust" collapses from per-consumer to per-attestation.
74 bytes
Attestation size
vs 200–500 KB raw STARK
< 5µs
Warm verification
cached proof delivery
99%+
Hit rate
Production read-heavy workloads
Cross-verifier reuse
One attestation, every consumer
How they compose

Cachee + H33-74: three layers, one verifiable outcome

Cachee does not generate attestations. Cachee does not verify them. The architecture works because three independent layers compose: Cachee stores. H33-74 attests. Replay reconstructs.

Cachee stores
A verified outcome — STARK proof verification result, recursive composition intermediate, bridge state proof — is written to Cachee together with a reference to its H33-74 evidence element. Cachee delivers that outcome at sub-microsecond latency, with evidence-aware retention that preserves expensive-to-regenerate evidence references.
H33-74 attests
The 74-byte post-quantum evidence element is produced by H33 substrate at the moment the original computation runs. Signed by three independent post-quantum primitives (ML-DSA + FALCON + SLH-DSA). Opaque to Cachee.
Replay reconstructs
A downstream consumer fetches the cached outcome plus its H33-74 reference, runs H33's open-source verifier locally, and independently reconstructs the trust path — without trusting Cachee, without re-executing the STARK, without touching the H33 production pipeline.

This three-layer composition is what “verifiable computation caching” actually means: not Cachee acting as a trust anchor, but Cachee as the high-speed delivery layer for outcomes that H33-74 makes independently verifiable.

Post-quantum economics

Why post-quantum matters for zkEVM infrastructure

Modern zk infrastructure mixes hash-based primitives (which are PQ-secure) with elliptic-curve primitives (which are not). Pairings, KZG commitments, and EC-based recursion all assume discrete-log hardness — the same assumption that quantum computers are expected to break.

Cachee's attestations are post-quantum from inception. The 74-byte verification receipt is signed by three independent post-quantum primitives: ML-DSA (lattice), FALCON (NTRU lattice), and SLH-DSA (stateless hash). Breaking the attestation requires breaking three independent mathematical bets simultaneously.

The practical consequence: cached zkEVM verification receipts remain portable through the industry's migration to PQ-secure proof systems. Rollups, bridges, and prover networks built against Cachee today don't need to redo their trust assumptions when quantum computers arrive — or when NIST tightens the standards, or when an EC-side vulnerability is disclosed.

For long-lived zk infrastructure — settlement layers, restaking-backed prover markets, regulatory-grade rollups, multi-year proof archives — post-quantum portability isn't a feature. It's the only honest design choice.

Where it lands first

Sequencers, bridges, proof markets, and the long tail of zk verification

Concrete surfaces where portable proof verification pays for itself immediately.

Today
Every consumer re-verifies the proof
  • Sequencers re-verify each prover's proof before posting
  • Bridges replay full STARK verification per cross-chain message
  • Aggregators re-verify sub-proofs during recursive composition
  • Exchanges re-verify L2 state proofs before crediting deposits
  • Indexers re-process the rollup on every restart
  • On-chain verifiers burn L1 gas re-checking off-chain-verified proofs
With Cachee
Verify once. Trust everywhere.
  • Sequencer set reuses a shared attested verification
  • Bridges consume one verification receipt per proof, not per relay
  • Aggregators read cached recursive intermediates across composition
  • Exchanges trust the attestation, not the bridge they happen to use
  • Indexers boot from an attested checkpoint, not genesis
  • Lighter on-chain verifiers consume off-chain attested proofs

The pattern repeats anywhere a zkEVM proof is verified more than once: STARK proof caching, SNARK proof caching, recursive proof composition, bridge verification, sequencer compute, on-chain verification gas, prover network economics, L2 indexing, large proof delivery. Cachee compresses the verification cost from per-consumer to per-attestation — post-quantum, portable, and reusable.

Cross-chain reuse

One zkEVM attestation. Every chain that consumes Polygon state.

Polygon zkEVM doesn't live alone. Ethereum L1 settles its proofs. Bitcoin-anchored sidechains consume its bridge messages. Solana programs read its rollup checkpoints. Every one of those systems pays the full zkEVM verification cost today — and pays it per-consumer, per-chain, per-relay.

H33-74's evidence primitive — served by Cachee — is chain-agnostic. The 74-byte receipt produced by the Polygon zkEVM cache layer is the same primitive reused by the Bitcoin and Solana cache layers. A zkEVM proof, verified once on Cachee, is distributed as a portable computation receipt that a Bitcoin bridge, a Solana program, and any rollup with a Polygon dependency independently verify — without re-running the STARK, eliminating duplicated cross-chain proof verification.

This is what "cross-chain result reuse" actually means. Not a bridge token. Not a wrapped asset. The verification itself is the asset.

Same attestation primitive: ← Bitcoin ● Polygon zkEVM (this page) Solana →
Who this is for

Built for the zkEVM infrastructure layer

If you operate one of these and pay for proof verification compute repeatedly — Cachee turns that bill into a single attestation.

zk-rollup teams (sequencer + prover stack)
Bridge operators (cross-chain state proofs)
Prover networks (restaking-backed proof markets)
Rollup-as-a-Service (multi-tenant verification)
Sequencer ops (decentralized sequencer sets)
Aggregators (recursive composition)
Exchanges (L2 deposit/withdrawal proofs)
DEXes on zkEVM (state-proof-driven UX)
L2 indexers (restart-from-attested-checkpoint)
L2 RPC providers (serve attested cache, not raw provers)
Restaking operators (slashing-grade proof verification)
Settlement systems (regulatory-grade portable proofs)
Verification economics at scale

What changes when proof verification becomes a reusable asset

zk economics are dominated by two hidden costs: generating proofs (prover compute) and repeatedly verifying them (everyone downstream). The proof-generation cost is well understood. The repeated-verification cost is the invisible tax that compounds with every new consumer of the rollup.

Marginal cost of a new consumer collapses. Adding a new bridge, indexer, exchange, or DEX integration no longer means adding a new pass of STARK verification. The new consumer reads the existing attestation. L2 verification infrastructure stops scaling node fleets linearly with customer count.

Cross-system trust collapses to zero cost. Two systems that don't trust each other — a bridge and a rollup, an exchange and a DEX, an indexer and an explorer — agree on zkEVM state without either running prover infrastructure. Both verify the attestation; neither re-executes the proof.

The trust model shifts to post-quantum. Long-lived zk infrastructure built against Cachee inherits a 74-byte attestation that survives the EC → PQ migration. Settlement layers, restaking-backed prover markets, and regulatory-grade rollups design verification receipts that are never redone when the cryptographic ground shifts.

This is what we mean by zkEVM scaling infrastructure. Not bigger batches. Not faster provers. Verification that doesn't need to be repeated.

zkEVM keeps re-verifying the same proofs millions of times.
Cachee turns proof verification into a reusable asset.

Pair the Polygon zkEVM cache layer with Bitcoin and Solana — one post-quantum attestation primitive, three live integrations, cross-chain by design.