How it works

One layer.
Two integration points.

No system changes required. Works with your existing flow. Mnemo sits beside your embedding step on insert and your retrieval step on read.

01The flow

embed → use → verify → decide.

Storage is optional. A vector database is not required.

input
embed
store
retrieve
verify

Expanded: input → embed → store optional → retrieve → verify → decision.

Input
Documents, queries, products, indicators. Whatever your pipeline already accepts.
Embed
Your model produces a vector. Mnemo attaches identity to it.
Store (optional)
Send the vector to Pinecone, Weaviate, Qdrant, pgvector, Milvus, or skip storage entirely.
Retrieve
Your retriever queries the store, or your service hands the vector back directly.
Verify
Mnemo confirms the result came from your pipeline and has not been altered.
Decision
Your service uses verified results. Unverified results are excluded.
02SDK

Two calls in your application.

Wrap your embedding step with embed(). Wrap your retrieval step with verify(). Your model and your storage stay where they are.

embed()
Attaches identity to a freshly produced vector.
WHEN
Once per ingest, after your model returns.
verify()
Returns identity and integrity for a vector you read back.
WHEN
On retrieval, before the result reaches the model or the user.
from mnemo import Mnemo
mn = Mnemo()

# on insert
vec = model.embed(doc)
e   = mn.embed(vec, source="docs/policy.pdf")
store.upsert(e.vector)

# on retrieve
for r in store.query(q, top_k=5):
    result = mn.verify(r.values)
    if result.verified:
        ctx.append(r)
03Trust Guardian

Verification for agents and services.

Trust Guardian lets agents and services verify embeddings through a shared MCP interface.

Endpoint
https://mcp.trymnemo.com/v1/<workspace>copy
~/.config/mcp/clients.json
{
  "mcpServers": {
    "mnemo": {
      "url": "https://mcp.trymnemo.com/v1/<workspace>",
      "auth": { "type": "bearer", "token": "mn_live_..." }
    }
  }
}
Available actions
mnemo.verify
Check whether a vector matches a trusted source registered in this workspace.
mnemo.embed
Register a vector before insert. Returns the registered vector and a source UID.
Flow
01 · Agent
Reads an embedding from the vector store or another service.
02 · Verify
Calls mnemo.verify through Trust Guardian.
03 · Result
Receives identity and integrity. Proceeds or stops.
04Deployment options

Run it where it fits.

Use via API
Multi-customer hosted Mnemo. Free, Starter, Growth, and Scale plans. Get going in minutes.
Run inside your infrastructure
Enterprise option. Mnemo runs in your VPC. Deployment, SLA, and pricing scoped per engagement.
05See it in action

One embedding is verified. One is not.

Mnemo shows the difference before data moves through your system.

Identity and provenance stay visible across reads, transforms, compression, and system boundaries.

Verify latency: ...
Verified
Statusqueued
Sourcequeued
Decisionqueued
Detail
Identityqueued
Originqueued
Integrityqueued
Decisionqueued
Unknown
Statusqueued
Sourcequeued
Decisionqueued
Detail
Identityqueued
Originqueued
Integrityqueued
Decisionqueued
Tracked across the system
Verified
created
12:01:04
embedded
12:01:05
indexed
12:01:08
compressed
12:01:12
retrieved
12:01:15
verified
12:01:15
Unknown
created
12:02:11
embedded
12:02:12
indexed
12:02:16
compressed
12:02:21
retrieved
12:02:25
verified
12:02:26

Start verifying in minutes.

Create a workspace. Register a service. Issue a credential. Run embed. Run verify.