See Memtro work
31 short walkthroughs: the product, what each team does with it, and how it is secured. Each one links to the page that explains it.
Start here
Where agents remember your company
One question, answered from your CRM, support desk, ledger and warehouse, with every figure cited to its record.
Read the page →Quickstart
Your first request from curl, Python, JavaScript, OpenCode or Claude Code.
Read the page →
Product
API reference
Endpoints, model ids, the memtro extension, streaming and tools: everything an OpenAI-compatible client needs to talk to Memtro.
Read the page →Memory
How Memtro learns, personal versus shared knowledge, history as of any date, and importing from ChatGPT and Claude.
Read the page →Time travel
Read memory as of any date, follow how a fact changed, and ask what the company believed in July.
Read the page →Connectors
Every connected system, what the model can do with it, and how to connect it.
Read the page →Teams and permissions
Admins and users, teams, who can use which shared connection, and what users may set up.
Read the page →Model routing
The auto model: per-level ladders, the difficulty classifier, fallbacks, the coding ladder and the agent-mode floor, set per organisation, team or person.
Read the page →Cost control
A token allowance a month for each model choice: when one runs out the cheaper one answers, and a level with nothing left refuses instead of costing more.
Read the page →Agent mode
Multi-step investigations, cross-referencing, and how the loop is confined.
Read the page →Jobs
Scheduled actions created from chat or the dashboard: digests, monitors and reminders that run with their owner's tools and report back in a chat.
Read the page →Commitments
Who promised what in a meeting, by when, and whether the other systems show it landed.
Read the page →Contradictions
The things your business believes twice, differently — found by reading its own memory against itself, and corrected by answering them.
Read the page →Jargon
The words your business uses in its own way, and what they point at — so every answer starts from your usage rather than the dictionary's.
Read the page →Usage statistics
Tokens and requests by user, team, model and day, with CSV export, so the cost of every conversation is visible to the people who pay for it.
Read the page →Privacy and erasure
Answer a request to be forgotten: find everything held about a person, erase it across every store, and keep the receipt.
Read the page →MCP server
Use Memtro's tools from any MCP client: Claude Code, Cursor, Claude Desktop and your own agents get memory and connectors over one endpoint.
Read the page →Claude Code
Run Claude Code on Memtro as its model, add Memtro's tools to it, or run Memtro on your Claude Code subscription.
Read the page →
Use cases
Support: Answer tickets with the whole company behind you
Support teams spend their day switching tabs: the ticket in Help Scout, the customer in the CRM, the order in the warehouse, the invoice in Xero. Memtro reads the ticket and does the switching for them.
Read the page →Sales: Walk into every call briefed
Account history, open tickets, invoices, the last email thread and what was decided internally, pulled together from the systems that hold them and remembered for next time.
Read the page →Finance: Ask the ledger questions in plain English
Xero, Stripe and the warehouse answer through tools that read by default, and Xero can raise a draft invoice or record a payment when you ask and an administrator has granted it. Duplicate charges, aged receivables, revenue by segment: one question, with the figures cited to their source.
Read the page →Engineering: Keep decisions from evaporating
Decisions, owners and deadlines are extracted from conversations and tool results into a typed, time-aware memory. Corrections supersede old facts instead of piling up next to them.
Read the page →Operations: Monitors and digests that run themselves
Jobs are prompts the agent runs on a schedule with the same tools as their owner. Create them in plain language, get the report in a chat, pause or change them in a sentence.
Read the page →Leadership: One question across the whole company
Founders and managers ask what is happening and get an answer stitched from support, sales, finance and engineering, with every figure traced to its source and the rest of the week handled by jobs.
Read the page →Product: Hear what customers actually ask for
Feature requests are scattered across tickets, call notes, Slack threads and issues. Memtro reads them where they live, links them to the customers who raised them, and remembers which decision closed each one.
Read the page →Data and analytics: Questions answered from the warehouse, with the SQL shown
Point Memtro at a read-only replica and anyone can ask the warehouse a question in plain English. The agent reads the schema, writes the query, runs it inside a read-only transaction, and shows its work.
Read the page →People and onboarding: The answers a new hire would otherwise ask around for
Policies, who owns what, how things are done and why: Memtro learns them from documents, conversations and the systems you connect, and keeps personal matters personal.
Read the page →Marketing: Spend, leads and reputation in one conversation
Ad platforms, email tools, social pages, review sites and analytics each have their own dashboard. Memtro reads them all, so one question can cover what you spent, what it brought in, what customers are saying and what the CRM did with the leads.
Read the page →Agent builders: Memory and tools for the agents you build
Point your own agent at Memtro over the OpenAI-compatible API or MCP and it gets long-term memory, connectors that read by default and act where you grant it, and model routing without you building any of it.
Read the page →
Trust
Security
Encryption, connectors that read by default, per-fact scope, a confined agent and provenance.
Read the page →Privacy
How Memtro collects, uses and protects your data.
Read the page →