NewCost control: a token allowance a month for each model choice — when one runs out, the cheaper one answers.See how it works
memtro
Comparison

Memtro vs Glean

An enterprise work assistant sold by the seat, versus a memory layer your existing tools point at with your own model keys.

This comparison describes Glean as we understand it at the time of writing from its public materials. Products change; check the current details before deciding.

Glean is an enterprise work assistant built on a permission-aware search index across a company's SaaS systems. It is a destination: its own search experience, assistant and agent builder, sold as a seat subscription to larger organisations, with the models it uses chosen and operated by Glean.

Memtro is not a destination. It is an OpenAI-compatible endpoint and an MCP server that sits in front of the tools people already use — Claude Code, Cursor, Open WebUI, the OpenAI SDKs, your own agents — and gives all of them one memory, connectors that read by default, model routing and scheduled jobs. You bring your own model keys and the model usage stays on your provider account.

Where they differ

MemtroGlean
ShapeAn endpoint your existing clients point at, plus MCPA product people open, with its own UI and agents
ModelsYour keys, your choice, routed by difficulty per requestChosen and operated by the vendor
Model costBilled by your providers at your rates; no margin addedInside the seat price
What it storesA typed, bitemporal graph of facts with provenanceA permission-aware index of your documents and records
HistoryA corrected fact is superseded, not overwritten: read memory as of any dateIndex reflects current state
Pricing shapeOne price per organisation by headcount, from $50/monthEnterprise seat subscription
Who it suitsTeams that already have tools they like, and want them to share a memoryOrganisations that want one assistant everybody opens

Honestly, where Glean is stronger

Glean has been doing permission-aware enterprise search for far longer, and at the scale of tens of thousands of employees and hundreds of millions of documents that heritage matters. If what you want is a single search box that respects every ACL in a very large organisation, and you want one vendor accountable for the whole thing including the models, that is what Glean is built for.

When to choose which

Choose Glean if you are a large organisation buying a company-wide assistant as a product, with procurement and a seat budget to match, and you want the vendor to own the model decisions.

Choose Memtro if your people already work in editors, chat clients and agents they like, you want those to share one memory of the company rather than adopt a new destination, and you want the model choice — and the model bill — to stay yours. It also matters if you care about reading memory as of a date, or about every fact citing the record it came from.