Run expensive computation once. Prove it. Reuse it forever.
Instead of caching data, Cachee stores proven and signed computation results that can be reused instantly, verified independently, and shared across systems.
No recomputation. No trust assumptions. No infrastructure changes.
ZK is expensive once. Cachee makes it free forever.
VERIFICATION:
Cachee stores proven and signed computation results plus a reference to a 74-byte post-quantum evidence element produced by the H33 substrate at the moment of computation. The evidence element is signed by three independent post-quantum primitives (ML-DSA + FALCON + SLH-DSA).
A downstream consumer fetches the cached result plus its evidence reference, runs H33's open-source verifier (h33-verify) locally, and independently reconstructs the trust path - without trusting Cachee, without re-executing the original computation, and without touching any H33 production pipeline.
No Cachee. No H33. No network. Still verifies.
PERFORMANCE:
L0 GET: 31ns at 32M ops/sec single-thread
Value-size independent: same latency for 64B tokens and 49KB payloads
CacheeLFU adaptive eviction with constant 512 KiB admission filter at any keyspace cardinality
Cachee is the verifiable computation cache. Run expensive computation once. Prove it. Reuse it forever. Cachee stores proven and signed computation results that can be reused instantly, verified independently, and shared across systems. No recomputation. No trust assumptions. No infrastructure changes.
31ns L1 reads regardless of payload size. CacheeLFU adaptive eviction with constant 512 KiB admission filter at any keyspace cardinality. 140+ Redis-compatible commands at 32M ops/sec. L0 in-process / L1 regional / L2 federated hybrid tiering. Multi-tenant isolation with per-tenant quotas and rate limits.
No Cachee. No H33. No network. Still verifies. Composes with H33-74 post-quantum evidence elements (ML-DSA + FALCON + SLH-DSA). Open-source verifier (github.com/H33ai/h33-verifier) - downstream consumers independently reconstruct the trust path without trusting Cachee, without re-executing, without touching H33 production.
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
You pay based on how many cache operations you run, with no upfront commitment. Two usage-based dimensions handle the same activity at different measurement scales. The Cache Operations (Units) dimension bills per individual operation, such as GET, SET, MGET, and DEL requests. The Cache Operations Block (Units) dimension bills in blocks of 1,000,000 operations, letting you pay per block instead of per single operation. Both track the same cache activity, so you choose the counting unit that fits your volume. Charges scale directly with how many operations you process.
Top-of-mind questions for buyers
What counts as one cache operation for billing?
A cache operation is a single request Cachee processes, such as GET (read a value), SET (store a value), MGET (batch read), or DEL (remove a key). Each such call counts as one operation. The block dimension groups these same calls into units of 1,000,000.
How do the per-operation and per-block dimensions combine on my bill?
They measure the same activity, so you are not billed twice. You pick the counting unit that matches your volume. Per-operation billing counts each request individually. Block billing counts in groups of 1,000,000 operations. Charges scale directly with the operations you process under whichever unit you choose.
Does cost accrue when my application sits idle and runs no cache operations?
Billing is usage-based with no commitment or minimums. You pay only for the operations you process. When your application runs no GET, SET, MGET, or DEL requests, no operations are counted, so no operation charges accrue for that period.
www.cachee.ai
Helpful?
Vendor refund policy
We offer a full refund within the first 30 days if you are not satisfied with Cachee.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Additional details
Usage instructions
After subscribing, you will be redirected to complete your Cachee registration. You will receive your API key and deploy instructions immediately. One-command install on any EC2 instance in the same VPC as your ElastiCache cluster.
Support
Vendor support
Cachee.ai provides email support at support@cachee.ai with a response time of under 24 hours for all plans. Enterprise customers receive priority support with under 4-hour response time and a dedicated Slack channel. Documentation is available at https://cachee.ai/docs. For urgent production issues, contact urgent@cachee.ai.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Be the first to review this product. We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.