Sold by: Cachee
Run expensive computation once. Reuse it forever. Cachee stores signed computation results -- STARK verification, ZK proofs, ML inference, large PQ payloads -- that can be reused instantly, verified independently, and shared across systems. 31ns reads regardless of value size. 140+ Redis commands. Drop-in for existing workloads.
Overview
Cachee is a verifiable computation cache built for AI, ZK, and post-quantum systems.
Instead of caching data, Cachee caches computation results. When a computation runs, the result is signed by three independent post-quantum algorithms (ML-DSA-65, FALCON-512, SLH-DSA), bound to its full computation identity, and stored as a portable artifact.
That artifact can be reused instantly, verified independently, and shared across systems. No recomputation. No trust assumptions. No infrastructure changes.
USE CASES:
- STARK/ZK proof verification caching (25us to 85ns = 294x speedup)
- ML/AI inference result reuse (eliminate redundant GPU compute)
- Large PQ key material (ML-KEM 1,568B, SLH-DSA 49KB at constant 31ns)
- API response caching at any payload size
- Session validation, auth pipelines, risk scoring
PERFORMANCE:
- L0 GET: 31ns at 32M ops/sec single-thread
- Value size independent: same latency for 64B and 49KB
- Hit rate: 99%+ with CacheeLFU adaptive eviction
- 140+ Redis-compatible commands
VERIFIABLE:
- Every cached result signed by 3 post-quantum families
- Computation fingerprint binds result to exact inputs + parameters
- Standalone verification: cachee-verify bundle.cab (no account, no network)
- We do not need to exist for your system to be trusted
INSTALL: brew tap h33ai-postquantum/tap && brew install cachee cachee init && cachee start
7 PRICING TIERS:
- Free: $0 (1M ops trial)
- Pay-As-You-Go: $15/1M ops
- Starter: $199/mo (20M ops)
- Scale: $999/mo (200M ops)
- Institutional: $9,999/mo (10B ops)
- Institutional+: $24,999/mo (50B ops)
- Unlimited: $99,999/mo (no ops cap, 10TB memory, custom SLA)
Highlights
- Run computation once, reuse forever. STARK verification 294x faster (25us to 85ns). ML inference cached at 31ns. ZK proofs verified once, served instantly. Computation results signed by 3 post-quantum families.
- 31ns reads regardless of value size. 64-byte tokens and 49KB PQ signatures at the same latency. 140+ Redis commands, 32M ops/sec. In-process Rust engine with CacheeLFU in 512 KiB constant memory.
- Independently verifiable. Every result carries a computation fingerprint and 3 PQ signatures. Anyone can verify with open-source tools. No Cachee account. No network call. No trust required.
Details
Sold by
Delivery method
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
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.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/unit |
|---|---|---|
Cache Operations | Cache operations (GET, SET, MGET, DEL) processed through Cachee | $0.00002 |
Vendor refund policy
We offer a full refund within the first 30 days if you are not satisfied with Cachee.
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.
Delivery details
Software as a Service (SaaS)
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.
Similar products
Post-quantum authentication with FHE, STARK ZKPs, and Dilithium signatures. 2.2M auth/sec sustained. 35.25us per auth. Single ARM CPU. FIPS 203/204 compliant. SOC 2, HIPAA, ISO 27001.
Customer reviews
No customer reviews yet
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.