Now AvailableDedicated AI memory with cryptographic proofs. From $5/mo USD.View pricing →

Build vs. buy · Agent memory

Build your own retriever.
Or don't.

Our benchmark settled one thing: your agent needs memory — answer accuracy went from 0% without it to ~75%with it. You could match us on simple lookups by building keyword RAG yourself. The question is whether you want to build, tune, host, and maintain that — or drop in a managed memory layer that also does what RAG can't.

Where MMPM sits: the L2 cache for AI

L1
Context window
Tiny · fastest · volatile — cleared every session
L2
Parametric Memory — the L2 cache
Predictive prefetch (64% hit) · Merkle-verified · sub-ms recall · your hot working set
Main
Vector DB · knowledge base · files
Large · slow · cold storage

Your vector database is main memory. MMPM is the L2 cache in front of it — the fast, predictive, verifiable tier that keeps the right context warm before your agent asks. Verify a memory yourself →

Build your own RAG, or use MMPM

Capability
Build-your-own RAG
you own it
MMPM
managed
Simple keyword lookupYesYes — 100%
Multi-hop recall (answer shares no words with the question)No — 0% in testOnly arm that answered any
Verifiable provenance (Merkle proofs)NoEvery atom
Knowledge-graph edges (relationships, not chunks)NoBuilt in
Conflict detection (stale facts flagged)NoBuilt in
Cross-session persistenceYou build & host itBuilt in
MCP-native — drops into your agentYou wire itOne endpoint
Who builds, tunes, hosts & maintains itYouManaged for you
CostEngineering time + infraFrom $5/mo

The honest row is the first one: on simple keyword lookups, a RAG you build can match MMPM. Every row below it is what you'd still be missing — or still be maintaining.

What you're paying for

Managed

The retriever you don't build

No chunking, embeddings, vector database, or ops to run. MMPM drops into your agent over a single MCP endpoint — the memory layer is someone else's problem to keep alive.

Verifiable

Every memory, provable

Each atom is sealed in an RFC 6962 Merkle tree — tamper-evident and auditable. You can prove what your agent knew, and when. Keyword retrieval can't offer that.

Predictive

The right context before you ask

Markov spreading activation surfaces facts that share no words with your query — the one capability that beat keyword retrieval in our benchmark, and the reason memory is more than search.

One managed layer, priced to scale

Every tier ships Merkle proofs, Markov prediction, knowledge-graph edges, and MCP-native access.

Starter
$5/mo
1,000 atoms · shared
Solo
$9/mo
10,000 atoms · shared
Most Popular
Professional
$29/mo
100,000 atoms · dedicated infra
Team
$79/mo
500,000 atoms · dedicated infra
Enterprise
Contact
Custom · self-hosted option

The evidence behind the claims

A controlled retrieval + answer benchmark (Opus 4.8) on our real 3,716-fact production substrate. Deterministic and reproducible.

0% → ~75%
Memory is necessary

Answer accuracy with no memory (or a recency prompt) vs. with MMPM-retrieved context. The no-context control scored 0%, proving answers come from retrieval, not the model.

Only MMPM
Answered multi-hop

On questions whose answer shares no words with the query, keyword RAG scored 0/18. MMPM was the only method to answer any (directional; small sample).

100% = 100%
Tie on simple lookups

On direct keyword lookups (n=48), MMPM and keyword RAG both answered 100%. We report where the baseline wins — it's what makes the rest credible.

Retrieval-side: a recency-maintained prompt surfaced the needed fact 0 of 48 times even at a 32,000-token budget; MMPM surfaced it using about 500 tokens — the same answer on roughly 0.2% of the tokens.

Questions people ask

Can't I just build this with a vector database?+

For simple keyword lookups, yes — in our benchmark, keyword retrieval tied MMPM at 100%. But that's a retriever you build, tune, host, and keep alive, and it still can't do multi-hop recall, give you Merkle-verifiable provenance, a knowledge graph, or conflict detection. MMPM is all of that, managed, from $5/mo.

So does MMPM actually beat RAG?+

On simple keyword lookups, no — it's a tie (both answered 100%). We say that plainly. MMPM's edge is threefold: multi-hop recall (it was the only method to answer any multi-hop question in our test), cryptographic verifiability, and the fact that it isn't your team's problem to operate.

Is the benchmark run on a real system?+

Yes — on our own production substrate, the same one we run our SaaS on, hardened across many revisions. Not a toy corpus. The numbers are deterministic and reproducible; the harness, probes, and seeds are in the repo.

Why did the no-memory baseline score 0%?+

The facts are private to the substrate, so the model can't know them from training. With no retrieval it correctly refuses rather than guessing — which is exactly why any score above zero is attributable to the memory layer, not the model.

What do I actually get at each price?+

Every tier ships the differentiators — Merkle proofs, Markov prediction, knowledge-graph edges, MCP-native — and scales on atoms and infrastructure: Starter ($5) and Solo ($9) on shared infra, Professional ($29, most popular) and Team ($79) on dedicated infrastructure, Enterprise on custom or self-hosted.

Skip the retriever. Keep the memory.

Verifiable, connected, and predictive memory behind one MCP endpoint — from $5/mo.