01
Recall that compounds
Cross-session memory with hybrid search. The engine decides what's worth keeping, so context carries from one conversation to the next without bloating your prompts.
NewBrain Store — browse public brains→Give any AI
Expertise your AI can install
Give any AI
an expert brain.
A brain is a domain-scoped memory — grounded facts plus the reasoning to use them. Connect it to Claude Code, Cursor, or your own app over MCP, and every answer traces to a source. It remembers across sessions, forecasts what's next, and a local model with the right brain matches a frontier one — at a fraction of the cost.
Open SDKs · Patent-pending · Hosted or on-device
recall edges in ink · predicted next events in purple
One command
to install into Claude Code
MCP + SDK
drop-in for any agent
Hosted or local
run it your way — private by default
GDPR
export & erasure built in
The result
We beat Mem0 and Zep on LOCOMO — at 13× fewer tokens.
Every memory vendor grades LOCOMO with its own lenient judge, so we didn’t invent a friendlier one. We scored our engine under each competitor’s own judge — Mem0’s partial-credit rule, Zep’s “same-topic” rule — and win overall against both, leading temporal, single-hop, and multi-hop.
vs Mem0
76.6 vs 66.9Scored under Mem0’s own partial-credit judge
Temporal78 / 55
Single-hop78 / 67
Multi-hop75 / 51
Open-domain74 / 73
Overall76.6% vs 66.9%
vs Zep
70.2 vs 66.0Scored under Zep’s own “same-topic” judge
Temporal75 / 49
Single-hop75 / 62
Multi-hop52 / 41
Open-domain70 / 77
Overall70.2% vs 66.0%
13×fewer tokens per query
Most memory systems buy accuracy by flooding the context window — Mem0 stuffs up to 200 memories into every prompt. We feed the model 522 tokens, not ~7,000. Same questions, better answers, a fraction of the cost. This one needs no judge.
522MemMesh
7,000Mem0
LOCOMO, 10 conversations, answerable categories · production extraction path · gpt-4o-mini answerer, gpt-4o judge · competitor figures are their published LOCOMO numbers. Zep edges us on open-domain — their strength, shown as-is.
Live demo
Same question. One remembers — and predicts.
A stateless assistant starts from zero every time. Your MemMesh MeshKey recalls what matters — and tells you what’s next.
M
Your MeshKey
PRIVATEENCRYPTEDPORTABLE
13,247
Entities
327
Agents
410K
Messages
1,021
Predictions
766
PDF
47
Video
199
Images
93
Skills
What's in my memory — and what's next?
AI
AI without MemMesh
ChatGPT · Claude · any LLM
MM
AI with your MemMesh
Claude Code · Cursor · your memory
Specialized brains
Grounded domain answers you can verify.
A brain is a ready-made memory for one domain — the facts for a subject like SEC filings, plus the know-how to use them. Point any AI model at it, and every answer comes straight from that brain's data, and only that brain's data. No made-up numbers — every answer links back to the exact source it came from.
| Answerer | Brain | Accuracy | Cost / q |
|---|---|---|---|
| Llama 3.1 8B (local) | — | 0.0% | $0.0007 |
| GPT-4o (frontier) | — | 0.0% | $0.0012 |
| Llama 3.1 8B (local) | 96.5% | $0.0007 | |
| GPT-4o (frontier) | 96.5% | $0.0018 |
34 SEC-finance questions graded against real 10-K filings (data.sec.gov). Same judge, dataset, and prompt across rows.
Without the brain, both models score 0%.
That's the point: these are precise, recent filing figures no model holds on its own. So every correct answer is provably the brain's — not the model's. A small local model with the brain matches a frontier model with the same brain at roughly 2.5× lower cost per question ($0.0007 vs $0.0018) — and near-free when you self-host the local model.
We're pushing each brain toward 99% — the ceiling is the brain's data, not the model, so every correction we add lifts the number without retraining anything.
And it doesn't stop at one brain. The Mesh Router gives a single endpoint across every brain a key can reach — owned, purchased, or pinned — so one call routes and pulls across all of them, with per-brain provenance on every result.
Full dataset, harness & per-question verdicts are public.
Inside a brain
What makes a brain more than a custom GPT.
A prompt-stuffed custom GPT forgets between sessions, guesses when it's unsure, and can't show its work. A MemMesh brain remembers what matters, forecasts what happens next, and traces every claim to a source.
02
Foresight, not just recall
MemMesh mines behavior into patterns and forecasts the next event. Every forecast carries a confidence score, checked against what actually happened and recalibrated over time. When it says 80%, it means it.
03
Governed by scope
Every memory has a scope — user, team, org — and provenance on every claim. GDPR export and erasure are built in, so you stay in control of what's remembered and why.
Products
Three ways to ship a brain. One engine underneath.
Packaged brains for people and teams — and the raw engine layers for builders who want the primitives.
Product→
MeshKey
One key. Your memory, in every AI.
A private, portable memory that unlocks in every AI tool you use — Claude Code, Cursor, ChatGPT. One key carries your context, preferences, and history wherever you work.
memory.observe · memory.search · MCP
Product→
Team Brain
Shared memory your whole team can trust.
A governed org memory: a shared knowledge graph with scopes, provenance, and compliance built in — so institutional knowledge stops disappearing every time someone switches context.
scopes · provenance · compliance
Product→
Mesh Router
The gateway that wires any agent into the mesh.
The infrastructure layer: an MCP gateway plus SDKs in five languages that connect any agent, tool, or app to MemMesh — one API for observe, recall, and predict.
MCP gateway · SDKs (TS · Py · Go · .NET · Rust)
The engine
Engine→
Memory
Recall that compounds.
Cross-session persistent memory with hybrid search and a knowledge graph. The engine decides what's worth keeping, so context carries between conversations without bloating your prompts.
memory.observe · memory.search · memory.reflect
Engine→
Predictions
Foresight, not just recall.
Declare any target and the engine predicts it from a subject's history — calibrated, provenanced, and abstaining when the signal is thin. This is the layer mem0 and MemoryLake have no answer for.
lattice.predict (event · numeric · time · anomaly)
Engine→
Behaviors
From patterns to next-best-action.
The engine mines behavior into emergent patterns and closes the loop: predict, let the agent act, record the outcome, and watch the patterns recalibrate. Decisions and outcomes are first-class.
lattice.mine · learning.recordDecision / recordOutcome
Quickstart
Wire up memory in minutes.
One command to install, three primitives to use: observe, recall, and search.
agent · terminal
# Wire MemMesh into your agent in one command
npx @memmesh/cli install
# Then, from inside your agent — three primitives:
memory_observe({ text: "Customer prefers email over phone." })
memory_recall({ subjectId: "cust_42" })
# -> prior context, with provenance
memory_search({ query: "communication preferences", limit: 5 })How it works
Observe, learn, recall.
It's how a brain learns — the same loop at every scope, from your personal brain to an org's. Feed it raw text; the engine does the rest.
- STEP 01
Observe
Feed MemMesh raw text or typed observations from your agent. One call — memory.observe — and the engine decides what's worth saving.
- STEP 02
Learn
It distils observations into a knowledge graph, mines behavior into patterns, and calibrates predictions against what actually happened.
- STEP 03
Recall
Search, recall, and predict. Your agent retrieves relevant context — with provenance — and gets a calibrated forecast of what's next.
Solutions
Expert brains for the industries that lean on them.
The same grounded recall-and-prediction, tuned into a domain brain for the industries that need it most.
Finance & investing
→From stateless advisors to trusted partners.
Portfolio-aware AI that remembers a client's holdings, risk profile, and prior calls — and makes calibrated buy/sell/hold decisions with a self-improving reconcile loop.
Healthcare & life sciences
→Memory that's audit-ready by construction.
Optional health estimators, provenance on every claim, and audit-ready retention with export and erasure — for teams that operate under real compliance requirements.
Commerce & retail
→Predict what each shopper wants next.
A memory of every shopper — preferences, history, intent — plus a forecast of the next purchase and the moment to make the offer. The predictive-wallet pattern, on your storefront.
Customer support & CX
→Every customer remembered across every channel.
Carry each customer's history and preferences across conversations and channels, self-correct when facts change, and surface what they're likely to need before they ask.
Use cases
One brain primitive, every team.
The same observe-learn-recall loop, shaped into a brain for the way each team works.
- 01
Engineering & dev agents
Drop persistent memory into Claude Code, Cursor, or Codex via MCP in one command. A new teammate opens their editor and the agent already knows the project.
- 02
Sales & revenue
Give every rep and every AI SDR a memory of the account: past calls, objections, commitments — and a calibrated forecast of what closes next.
- 03
Marketing & growth
Remember every segment, campaign, and creative decision — and predict the offer and send-time each user is most likely to act on.
- 04
Support & success
Carry every customer's history, preferences, and prior decisions across conversations — and surface what they're likely to need next.
- 05
Research & analytics
Turn scattered findings into a durable, queryable knowledge graph with provenance on every claim — and calibrated estimates where the data is thin.
- 06
Operations & compliance
Audit-ready retention, GDPR export and erasure, and scoped memory for teams that operate under compliance requirements.
How we compare
The field is great at remembering. Two things stay open.
Mem0, Zep, and MemoryLake are strong memory layers — Zep's temporal graph and MemoryLake's provenance are genuinely good. But none of them forecast what happens next, and none let you install or publish a specialized brain. That's the ground MemMesh is built on.
| Capability | Mem0 | Zep | MemoryLake | MemMesh |
|---|---|---|---|---|
| Cross-session memory | ||||
| Knowledge graphstructured, related recall | ||||
| Provenance on every claimtrace an answer to its source | — | |||
| Calibrated forecast of what's nextprediction, not just recall | — | — | — | |
| Specialized brains you install & publisha marketplace of domain expertise | — | — | — | |
| Flows + 681 connectorsautomate memory across your tools — like Activepieces, for memory | — | — | — | |
| Hosted or on-device, private by default | — |
yes partial— no / not advertised
Capability comparison from each product's public docs, July 2026 — not a benchmark, and capabilities change. We credit the rest where they're strong and compare only on the axes we're built for.
Read the full comparisonsEnterprise & compliance
Governed by design, not as an afterthought.
MemMesh ships the controls regulated teams ask for: scoped access, data portability, audit trails, and right-to-erasure. On Growth and up, the compliance toolkit — export, audit, hard-delete — is on by default.
SOC 2-aligned describes our controls and roadmap, not a completed certification.
Governance by scope
Memories are scoped to user, team, or org, with provenance on every claim — so you can answer who knew what, and why.
Portability
Full GDPR-style export. Your memory is yours; take it with you at any time.
Auditability
Audit trail with configurable retention — up to seven years on Enterprise — plus right-to-erasure on compliance tiers.
Deployment control
Run it your way — hosted, in your VPC, or fully on-device. Private by default, with data-residency options for teams that need data to stay put.
Pricing
Start free. Scale on what you remember.
Subjects are the headline ladder, predictions are the value meter, and events are generous fair-use. Yearly is two months free.
Free
$0forever
Wire memory into your agent and ship your first project.
Growth
Popular$79/mo
Scaling teams — more projects, compliance, prediction overage.
Enterprise
Custom
Unlimited scale, on-device deployment, 7-year audit retention.