Mnemo

Verify every embedding
before it is used.

Provenance and lineage for AI systems.

Attach identity to every embedding and verify it when it is used. Works with your existing system. Two calls to get started.

Use via API or run inside your infrastructure.

One SDK
Two calls. embed and verify.
Any vector store
Pinecone, Weaviate, pgvector, Milvus.
Agent compatible
Trust Guardian over MCP for agents and tools.
Drop-in
Works alongside your existing model and store.
01Where Mnemo sits

Between your embedding model and your system.

On insert, Mnemo attaches a signed identity to the embedding. On retrieval, your services confirm the embedding came from a known source and has not been altered. Works with your existing system.

input
embed
store
retrieve
verify

Two integration points: embed() and verify(). Storage is optional. No vector database required.

02Use cases

If you generate embeddings, Mnemo applies.

03Setup

Two calls. Works with your existing system.

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

from mnemo import Mnemo
mn = Mnemo()

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

# on retrieve
for r in store.query(q, top_k=5):
    if mn.verify(r.values).intact:
        ctx.append(r)
04Scope

What Mnemo does not do.

Does not detect prompt injection
Does not analyze model weights
Does not moderate content
Does not replace your system

Mnemo focuses on one layer: attaching identity to embeddings and verifying them when they are used.

Start verifying in minutes.

Create a workspace, register a service, issue a credential, and run your first verified embedding. The free tier covers small pipelines.