Your AI's memory
should belong to you.
Edwin verifies what it knows, challenges what it believes, and stores it all on Walrus — where only you control it.
Every AI remembers. None of them check.
ChatGPT, Gemini, and Claude all store what you tell them. But they never verify it. Tell ChatGPT you're a doctor and it will remember that forever — no questions asked.
Blind Trust
Your AI stores everything you say as fact. No verification, no challenge, no second opinion.
Data Capture
Your memories live on their servers. You can't export, verify, or port your data to another platform.
No Proof
There's no audit trail. You can't prove what your AI knew, when it learned it, or whether it was right.
Where does Edwin fit?
Every AI company stores your data. Some verify it. Only Edwin does both and gives you ownership.
How Edwin is different
Three capabilities that no other AI memory system provides today.
Your AI never silently stores a lie.
Multiple AI models fact-check every claim before it enters memory. Errors that fool one model get caught by another. Common misconceptions, outdated facts, and hallucinations are blocked at the gate.
Your knowledge gets smarter while you sleep.
Edwin periodically stress-tests what it knows. Facts that hold up get stronger. Facts that crumble get re-examined. Your knowledge base self-corrects without you lifting a finger.
You can prove what your AI knew, on any date.
Encrypted, signed snapshots stored on Walrus — a decentralized storage network. Nobody can alter what was recorded. Your AI's memory has a tamper-proof audit trail that you control with your own keys.
Edwin audits itself — and improves with every version.
Edwin is the first AI system that evaluates its own components. When internal testing revealed a verification layer with zero precision, Edwin detected the failure and disabled it automatically — improving overall accuracy. Each version builds on the last, with Edwin's own test results guiding what gets fixed next.
14 versions shipped. Each one better than the last.
See it in action
A real scenario showing how Edwin protects your most important information.
You share a fact
Edwin protects you
Your data follows you
We don't just claim this works. We measured it.
6 of 7 scientific claims now have statistical evidence. Tested on a 200-fact controlled dataset across multiple independent runs.
| Metric | Edwin | Without Edwin | What It Means |
|---|---|---|---|
| Effective accuracy | 93% | 63% | +30 percentage point improvement with verification |
| False fact catch rate | 99% | ~0% | 75 of 76 false facts caught before storage |
| False positive rate | 4% | N/A | True facts rarely blocked — conservative by design |
| Data integrity | 100% | N/A | Every snapshot survives encrypt, upload, download, decrypt |
200-fact golden dataset. 13 categories. Multiple independent runs. No cherry-picking.
Request the full technical assessmentWhy Walrus? Because your data deserves better.
Walrus is a decentralized storage network — think of it as a global hard drive that no single company controls. Your data is encrypted, distributed across independent nodes, and accessible only with your keys. This isn't crypto speculation. It's infrastructure for data ownership.
Decentralized technology isn't just for crypto or NFTs. The same principles that make blockchain tamper-proof — distributed consensus, cryptographic signing, immutable records — are exactly what AI memory needs. Edwin uses this infrastructure for what it was designed for: provable data integrity.
Every Edwin user is a Walrus user.
Each knowledge snapshot goes to Walrus. More Edwin users means more storage demand. Edwin grows the ecosystem organically.
Recurring storage, not one-time.
Unlike one-time storage, AI memory is write-continuous. Background consolidation generates new snapshots every cycle, creating sustained demand.
Data sovereignty, made real.
The industry has talked about data ownership for years. Edwin makes it tangible for every AI user — not just developers or crypto enthusiasts.
The Storage Math
Walrus Integration Roadmap
Under the hood
A continuous loop from voice to verified, sovereign knowledge.
Edwin uses a multi-stage verification pipeline. Claims are checked by multiple independent AI models before entering a living knowledge graph. Background consolidation continuously stress-tests stored knowledge. Every verified fact is encrypted, signed, and stored on Walrus with full provenance.
Request the technical paperWhat's built, what's next, what we need.
Built & Working
- Voice pipelineNatural conversation interface
- Multi-model verificationCross-model fact-checking
- Veracity gate99% false fact catch rate
- Walrus integrationTestnet, 100% integrity
- Comprehensive test suite200-fact golden dataset, 13 categories
- Sleep consolidationAutonomous knowledge improvement
- Knowledge graph emergenceCross-domain integration (25σ above random)
- Self-diagnosisEdwin evaluates and improves its own components
Coming Next
- Sui on-chain integrationProgrammable knowledge proofs
- First 100 usersControlled early access program
- Standard benchmarksFEVER, LIAR dataset evaluation
- Mainnet deploymentProduction Walrus storage
- Adaptive mode switchingAuto-tuning model selection
- Enterprise complianceEU AI Act readiness
- ZK selective disclosureProve claims without revealing data
Built by Alexander Snyder + Edwin
Verified, sovereign AI memory that you own.
Alexander Snyder
Head of Data Strategy & AI at PurviewX
Edwin is a passion project born from real frustration with AI memory.
I started Edwin because I watched AI assistants confidently store wrong information and realized there was no way to verify, own, or port my data. The AI companies building memory features have no incentive to let you check their work or take your data elsewhere.
Edwin is my answer: an AI memory system that treats verification as a first-class feature and puts ownership in the hands of the user, not the platform.
“Validation-first development. Every claim on this site is backed by a controlled experiment, not a pitch deck. The 200-fact golden dataset and self-diagnosis capability represent more engineering rigor than most funded teams produce.”
Questions investors ask
Straight answers, backed by data.
Ready to own your AI's memory?
Edwin is in pre-launch testing. We're opening early access in waves.