Conversational

MemStrata Conversational - Private AI Memory with Evidence

Recall conversations and documents with temporal context, citations, OCR, and optional visual retrieval.

Who it is for: Knowledge and support teams that need private memory over chats and documents, with visible evidence.

Install Conversational Compare products

Five-minute flow

  1. 01

    Install

    Install memstrata-conversational from PyPI on Linux x86_64 and run memstrata-conversational init.

  2. 02

    Add sources

    Bring in conversation archives, notes, or documents. Connectors are explicit, not implied.

  3. 03

    Ask with evidence

    The retriever selects pages. The configured reader answers. Citations stay visible.

Cited answer with source pages

A retriever is not the final answer model. Visual retrievers select pages. The configured local or BYOK reader produces the answer, with source-page references.

evidence receipt

product: conversational

output: Recall conversations and documents with temporal context, citations, OCR, and optional visual retrieval.

proof: visible on device

Capabilities

  • Conversation archives, notes, documents, and explicit connectors
  • Nomic text retrieval for text and chat memory
  • Tesseract OCR for scanned documents
  • Optional ColQwen2, ColFlor, ColPali, or EVIE-family visual retrieval only when a compatible runtime is installed
  • Visual retrievers select evidence pages; a configured Rung 1 or trusted Rung 2 reader produces the answer

Privacy and data flow

Privacy-critical content and indexes remain on the device by default. OAuth, signed entitlements, device registration, and bounded private decisions use MemStrata services. A user-selected cloud model or connector receives only the data required for that explicit operation. Credentials are stored in the operating-system credential vault, not in page content or analytics. Customer content is not used for training unless the customer separately opts in.

Feature Local data 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
Memory, OCR, and optional visual retrieval Conversation archives, notes, documents, and selected evidence pages Selected evidence and question to a local or BYOK reader Explicit question or configured reader call Operating-system credential vault

Install and trial

Use the complete product free for 180 days. No subscription is needed during the trial. A paid entitlement is required only after the trial ends.

The 180-day trial begins after successful product activation. Product functionality remains enabled during the trial. MemStrata-managed email is limited to one message per signed-in user per UTC day. Reinstalling does not restart access. A paid entitlement is required after the trial.

PyPI · Linux only · 0.7.5

python -m pip install memstrata-conversational

sha256 64c1a2797de891508a8535b492a8901f428196a3c0edd962b39540e003e09a3a

Current latest PyPI file is Linux only.

  • microsoft store

    Coming soon

  • mac app-store

    Coming soon

  • snap store

    Coming soon

Integrations: Local reader, BYOK cloud reader, Document ingest, OCR

FAQ

Does visual retrieval answer the question by itself?

No. Visual retrievers select evidence pages. The configured reader produces the answer.

Is managed email unlimited during the trial?

No. MemStrata-managed email is limited to one message per signed-in user per UTC day.

Install Conversational