Memory with its shape intact
AIZK is an AI Zettelkasten for people, teams and agents. It connects what you learn without flattening sources, history or access boundaries.
- private by default
- five MCP tools
- open source
See your memory
Know what your agents know
AIZK is more than a hidden vector index. Browse sources, inspect findings, follow subjects, watch processing and see how memory is being used.
aizk
AI Zettelkasten
Dashboard
Your memory at a glance
Documents
87
Files
12
Findings
184
Subjects
61
Themes
9
Memory activity
Keep, find and share
Processing
Sources stay usable while enrichment continues
Recent sources
- Retrieval design notesprivate
- Interface guidelinesDesign
- Release checklistEngineering
Connected knowledge
Subjects remain linked to their evidence
Illustrative data. Your dashboard is built from the memory visible to your account.
One memory
Useful without losing context
Private by default
Your memory stays yours until you deliberately name who may share it.
Learn moreSources stay attached
Every answer can show where it came from and what the system derived later.
Learn morePortable by design
Five MCP tools keep the same shape across agents, teams and deployments.
Learn moreHow it works
Writing and reading are two paths through the same memory. Tap any box to jump to the part of the docs that explains it.
Sharing is a set, not a switch
Every memory carries the set of groups it belongs to. Reading requires standing in all of them, so naming two groups creates a shared cell that only people in both can reach. The access boundary stays attached when agents search, derive findings, or share a source.
- Writing names one destination. An agent picks the scope deliberately and the default is private.
- Reading spans everything visible. One question searches the union of what you can see, and the answer says where each piece came from.
- Sharing copies, it does not move. The private original stays yours and unchanged.
┌───────────────┐
│ { A , B } │ both organizations
│ intersection │ the narrowest shared cell
└───────┬───────┘
┌───────────┴───────────┐
┌─────┴─────┐ ┌─────┴─────┐
│ { A } │ │ { B } │
│ one team │ │ one team │
└─────┬─────┘ └─────┬─────┘
└───────────┬───────────┘
┌──────┴──────┐
│ { you } │ private
│ one person │ the default
└─────────────┘
a reader sees a row only when they stand in every scope it namesCorrections keep the past
aizk records two clocks for every claim. One is the time the statement was true in the world, the other is the time aizk was told. Correcting something closes the old range and opens a new one, so yesterday's answer can still be reconstructed and nothing is silently overwritten.
That matters when memory drives decisions. You can ask what the team believed in June and get June's answer, not today's, and you can see exactly when the belief changed.
How time worksWhat you get
Five tools, nothing else
status, find, keep, report and share. Any MCP client gets the whole product without an adapter.
Sources stay authoritative
The text you wrote is kept exactly. Everything the engine derives from it is a rebuildable projection that can be thrown away and rebuilt.
Grounded extraction
A fact is only written when the model can quote the span of text it came from. Ungrounded output is dropped rather than stored.
Files stay immutable
An original is scanned, hashed and stored behind an opaque key. Conversion produces derivatives beside it and never replaces it.
Speaker aware
Memory separates what is objectively true from what a particular person observed, prefers or experienced, so a team memory does not flatten into one voice.
One memory, not a pile of indexes
Notes, sources, derived claims, history and access boundaries stay connected, so an agent can show why each result belongs in the answer.