A memory layer for the AI tools you already use
Your AI forgets.
Edwin remembers, and shows its work.
Edwin remembers what you've told your AI — when it was true, what was decided, and what's actually been checked. It works with Claude today, and with any AI app that supports MCP, the open standard for connecting AI tools.
Asking Edwin costs about 125× less than pasting your whole history into the chat, at the same overall accuracy in our benchmark run. It reads about 0.3% of the tokens.
Self-run on STALE, a published benchmark of facts that change, Aug 2026 · See the measurement
Demo with fictional memories · what the colors mean
- Survived challenge
- Not confirmed
- Disputed
- Not yet challenged
You've explained it before. Your AI just doesn't remember.
It forgets
Every new chat starts from zero. You re-explain the same project, the same people and the same decisions, again and again.
It contradicts itself
Tell it the budget is $500K on Monday and $750K on Thursday, and you may get either answer back, with no sign of which one is current.
It can't show its work
Ask whether something is still true and you get a confident answer, with no date, no reason and no sign that anyone checked it.
Edwin fixes the memory underneath. Here's the difference when a number changes:
Memory you can trust, in six ways
Each one links to the record behind it.
It knows when things were true.
Every fact is saved with the date it was true. When the budget moves from $500K to $750K, Edwin records an update, not an error, and keeps the old figure on record with its date.
STALE benchmark, pre-registered, Oct 2026 (25.6% vs 13.1%) · See the experiment
Both values stay on record with their dates. The new one takes effect once two different AI providers agree it replaces the old one, or when you confirm it.
It keeps decisions in context.
Decisions from your meetings are kept as top-priority memories, tied to the meeting they came from and the facts discussed with them, so months later you can trace what was decided, when, and what was on the table.
It tells you what's been checked.
A second AI provider challenges facts in the background, and every memory carries a plain label: Survived challenge, Not confirmed, Disputed or Not yet challenged. You can always see whether a memory has been checked.
Pre-registered, Oct 2026 · See the measurement
- Survived challengeA second provider tried to dispute it and did not
- Not confirmedChallenged, but fell short of the bar
- DisputedThe providers that challenged it disagree
- Not yet challengedNo second provider has challenged it yet
It catches contradictions without crying wolf.
When two facts genuinely conflict, like two launch dates from the same meeting, Edwin flags the pair and keeps both. A contradiction only counts when two different AI providers agree or you confirm it.
Internal test, Apr 2026 · See the research
Neither is newer, so this is a real conflict, not an update.
Both facts stay on record until you decide.
It costs a fraction to ask.
Instead of pasting your whole history into every chat, your AI pulls only the memories a question needs. Edwin reads your history once; you don't pay to re-read it on every question.
Self-run on the STALE benchmark, Aug 2026 · See the measurement
It's yours.
Your memory is a SQLite file on your own Mac, with encrypted nightly backups. It works with Claude and any MCP-compatible AI client, so switching assistants doesn't mean starting over.
Local-first · Where your data goes
How it works
No new app to learn. Edwin sits underneath the AI tools you already use.
Connect
Edwin plugs into Claude and other MCP-compatible AI tools, and picks up your Otter.ai meeting exports.
Date, link and check
Each fact is saved with the date it was true, linked to related facts and the meeting it came from, and challenged in the background by a second AI provider.
Ask
Your AI pulls just the memories a question needs instead of re-reading your whole history. Old values stay on record with their dates.
For developers: a memory layer you can inspect
Plain files, an open protocol, and checks you can see.
A SQLite file you own
The whole store is one SQLite file on your Mac. Copy it, back it up, or query it with any SQLite tool.
Speaks MCP
Claude and any other MCP-compatible client can read memories and save new notes through Edwin's MCP server.
A dated, linked graph
Facts carry the date they were true, decisions stay linked to the meeting and facts around them, and replaced values stay on record.
More than one provider
Facts are read by one AI model provider and challenged in the background by a different one, and every memory shows whether that has happened yet.
Encrypted backups
Encrypted backups go every night to a location you control (iCloud Drive by default), under a key you hold.
What it takes in
Otter.ai meeting exports, and the notes your AI clients save over MCP.
Local-first, not local-only. Your memory lives on your Mac. To extract and check facts, Edwin sends text to AI model providers, and encrypted nightly backups go to a location you control (iCloud Drive by default). What leaves your Mac
Built to be checked. The measurement record is public.
We publish our measurement record, including what didn't work, because memory you rely on should be measured in public.
Built by Alexander Snyder
Alexander Snyder
Inventor of Edwin
I built Edwin because I watched AI assistants confidently store wrong information, and I wanted a memory I could check, keep on my own machine, and take to any assistant.
Your memory should belong to you, and every claim about it should be something you can check. That's why the results on this page link to the measurement record.
Questions
Short answers, with links to the detail.
What is Edwin?
Edwin is a memory layer for the AI tools you already use. It remembers what you've told your AI — when each fact was true, what was decided, and what's been checked — and serves it to Claude or any MCP-compatible client. Your memory is a SQLite file on your own Mac.
Who is it for?
People who use AI tools every day and are tired of re-explaining themselves, developers who want a memory layer they can inspect and query, and anyone who needs to trace what was decided, when, and what was on the table.
Why not just paste everything into the chat?
Because you pay for every token, on every question. In our STALE benchmark run, Edwin answered from about 0.3% of the tokens at the same overall accuracy: about 125× cheaper per question, with setup paying for itself after about 3 questions (self-run, Aug 2026). See the measurement
How do I know what's been checked?
A second AI provider challenges facts in the background, and every memory carries a label: Survived challenge, Not confirmed, Disputed, or Not yet challenged. Checking facts and showing the AI those labels raised accuracy 5.8 points on the STALE benchmark (pre-registered, Oct 2026). See the measurement
What happens when two facts disagree?
If one is newer, Edwin records it as an update and keeps the old value with its date. If two facts genuinely conflict, Edwin flags the pair and keeps both; it only counts as a contradiction when two different AI providers agree or you confirm it. On its own, Edwin's contradiction detector raised zero false alarms on a 150-pair test while catching 68 of 100 real contradictions (internal test, Apr 2026). A second-provider check now sits on top of it.
How is Edwin different from other AI memory tools?
Edwin puts four things in one memory you own: the date each fact was true, decisions kept with the meeting and facts around them, a label on every memory showing what's been checked (in a pre-registered test, checking facts and showing the AI those labels raised accuracy 5.8 points), and a SQLite file on your own Mac that works with any MCP client. See the research
Where does my data live?
Your memory is a SQLite file on your own Mac, with encrypted nightly backups to a location you control (iCloud Drive by default). To extract and check facts, Edwin sends text to AI model providers; the privacy page names each one. What leaves your Mac
When can I use Edwin?
Edwin is in private development. Email alexander@purviewx.ai and we'll tell you when it opens.
Give your AI a memory you can check.
Edwin is in private development. Email us and we'll tell you when it opens.
Evaluating Edwin in depth? The benchmark harness and spend ledger are available on request.