Four products. Local installation. The reader you choose.

Structured

Ask your operational records what is current and what changed.

Report on current and historical records. Operations teams that need current-state, history and change answers with a witness, or an honest refusal.

Full product access for 180 days after activation. No subscription during the trial.

Two incident records and an owner change

Illustrative

Record

INC-104

Was

Sam Ortiz

Now

Jordan Lee

Who owns incident INC-104 now?

Jordan Lee. Effective 12 March. Witness attached.

Local workspace Structured
Placeholder. Import preview with Record identity, Effective time and selected fields, then an owner change.

Two incident records and an owner change

Import a fictional pair of incidents. Change the owner on one. Ask who owns it now and what changed. Forecasting and arbitrary analytics are refused.

  1. 01

    Install

    Use the platform-specific command. Windows uses the GitHub 0.7.3 wheel, not an unpinned PyPI install.

  2. 02

    Map records

    Set a stable record key and effective time. A composite of policy name plus table name is one example, not the right key for every dataset.

  3. 03

    Ask what changed

    Import two records, update an owner, then ask the supported change question.

Answer, witness, or refusal

A supported question returns the answer, source witnesses and hashes. An unsupported or predictive question is refused instead of guessed.

What it does

  • Import preview with Record identity, Effective time and selected fields
  • Deterministic answers for supported current, count, owner, history, comparison and as-of questions
  • Import date records a snapshot. It does not reconstruct unavailable history
  • Windows 0.7.3 is the repaired wheel. Linux remains on PyPI 0.7.2. macOS 15 Apple silicon uses the GitHub 0.7.2 wheel

Prerequisites

  • Python 3.10 or newer
  • A CSV, Excel or Parquet file with a stable record key. A date column is not required for every import
  • Windows x64 uses GitHub wheel 0.7.3. Linux x86_64 uses PyPI 0.7.2. macOS 15 Apple silicon uses GitHub wheel 0.7.2

Supported connections: CSV (file import), Excel (file import), Parquet (file import)

Data handling

The primary indexes and source processing run on your device. Account services and selected bounded policy decisions use MemStrata services. A cloud reader or destination receives the content needed for the connection you choose. Credentials are stored in the operating-system credential vault. Customer content is not used for training unless the customer separately opts in.

Feature Local material Possible outbound Trigger Credential location
OAuth, signed entitlements, and device registration Device and entitlement cache Identity and device-bound entitlement fields Sign-in or refresh Operating-system credential vault
User-selected cloud model or connector Local evidence selection and indexes Only the data required for that explicit operation User configures and sends the request Operating-system credential vault
MemStrata-managed email Local alert or report draft Minimized message and recipient User-configured delivery; one message per signed-in user per UTC day during trial Server secret plus entitlement
Deterministic operational answers Mapped records, effective-time state, witnesses, and hashes None for core answers. Optional watches use confirmed connectors only User question; connector delivery only when configured Operating-system credential vault or customer provider

Install

Install MemStrata on Windows, Linux and Apple silicon

Full product access for 180 days after activation. No subscription during the trial.

Detected choices are a suggestion only. A browser cannot reliably know your macOS version or whether Python is installed. Python 3.10 or newer is required. On Windows, if Python is missing, install it from python.org/downloads/windows and open a new terminal. Microsoft Store Python redirects LocalAppData writes. The Windows command follows the real environment path after venv so pip is not pointed at an empty folder.

Architecture

x64

Shell

PowerShell

MemStrata Structured 0.7.3 · Windows x64 · Python >=3.10

Windows 10 or newer, x64. Next step after install: memstrata-structured.cmd init

PowerShell

$venv = "$env:LOCALAPPDATA\MemStrata\venvs\structured"
py -3 -m venv "$venv"
if ($LASTEXITCODE -ne 0) { throw 'Could not create the environment.' }
$python = "$venv\Scripts\python.exe"
if (-not (Test-Path -LiteralPath $python)) {
  $python = (py -3 -c "import os, sys; print(os.path.realpath(sys.argv[1]))" $python).Trim()
}
if (-not (Test-Path -LiteralPath $python)) { throw 'Could not create the environment.' }
$scripts = Split-Path -Parent $python
& $python -m pip install --upgrade pip
if ($LASTEXITCODE -ne 0) { throw 'Could not update pip.' }
$base = 'https://github.com/yadu9989/memstrata-binaries'
$release = "$base/releases/download/structured-0.7.3"
$wheel = "$release/memstrata_structured-0.7.3-py3-none-win_amd64.whl"
& $python -m pip install --only-binary=:all: "$wheel"
if ($LASTEXITCODE -ne 0) { throw 'Installation did not finish.' }
$actualVersion = (& "$scripts\memstrata-structured.cmd" --pypi-package-version | Out-String).Trim()
if ($LASTEXITCODE -ne 0 -or $actualVersion -ne '0.7.3') { throw 'The installed version does not match the advertised release.' }
Write-Output "Installed version: $actualVersion"
& "$scripts\memstrata-structured.cmd" init

memstrata_structured-0.7.3-py3-none-win_amd64.whl · sha256 63133a1dae1834a39f02f6eb574e1b9d2a834f784aff98d36f3f86f6392e61e0

Microsoft Store is a separate listing, not this wheel command. View Structured in Microsoft Store

Structured Windows uses the repaired 0.7.3 GitHub wheel. It does not fall back to PyPI 0.7.0.

180 days of full product access after activation. No subscription during the trial. Reinstalling does not restart it. Model-provider charges, if any, are separate. MemStrata-managed email is limited to one message per signed-in user per UTC day. For access after the trial, contact us about the appropriate paid entitlement. Trial terms

FAQ

Do I need an LLM?

No. Core deterministic answers do not require Ollama or a generative model.

Can I import a file with no date column?

Yes. You still map a record identity. Import date records a snapshot. It does not invent a history the file does not contain.

Why can records merge?

Rows that share the mapped record key are treated as the same entity over time. Choose a key that is actually stable in your file.

What questions are supported?

Current-state, count, owner, history, comparison and as-of questions over mapped records. Predictive and arbitrary analytics questions are refused.

Does this do forecasting or arbitrary analytics?

No. Those questions are outside the deterministic answer boundary.

Try Structured