Mnevra

Most “second brain” tools are filing cabinets: you do the remembering, they do the storing. Mnevra inverts it. You talk, by text or by voice, and it extracts the people, places, and events from what you said, deduplicates them into a knowledge graph, links them with typed relationships, and then does the thing no notes app does: it notices what you haven’t told it yet, and asks.

Your life is not one context, so the graph isn’t either. Spaces hold work, health, a project and home apart, each with its own tone, its own home screen and its own people. The only thing they share is you.

One question a day, at an hour you set

The system scores your accumulated memories against life chapters (early life, career, relationships, places) and identifies the gaps. Turn the daily check-in on and Neve, the resident interviewer, asks you about one of them: a single push, at a jittered time inside a window you choose, so it never arrives at 3am and never arrives on a schedule you could set your watch by. Behind that gentleness is a strict little state machine. Each gap tracks engagement, attempts and deferrals; two unanswered pushes park the topic rather than ask it a third day running; a topic you did engage with rests for 14 days. An interview never asks more than three questions on one gap, because the bar is “could write a paragraph from this,” not an interrogation. When you want the book, it’s generated chapter by chapter through Anthropic’s batch API and rendered to PDF in your choice of perspective, literary voice (Bryson, Didion, Sedaris, Hemingway, Angelou) and page design, with annotations feeding corrections back into the next edition.

Here’s what that actually produces. Soundtrack to a Life is a real chapter Mnevra interviewed out of me, one morning question at a time. I picked the Creative writing style, so the flourishes are the machine’s; the memories are mine.

Then: someone else’s story

The same machinery now points outward. Biography Mode mints a link you send to a parent or a grandparent, and what they open is a chat and nothing else: no graph, no settings, no app to learn. Neve asks them one warm question a day inside a window they set, and a dashboard in your own app shows how much of their life has been covered. When it feels done, you export their biography on their behalf. It is the feature that turned a personal tool into something you can hand to someone who will never install it.

The log is the truth

The architectural bet: every message, tool call, and result lands in an immutable log, and the entire knowledge graph is treated as derived state. When a better model arrives or an extraction prompt improves, one command replays the log and rebuilds the graph. In an AI system, “what did the machine conclude?” matters as much as “what did I say?” This design keeps both, forever, audited. Underneath, Postgres row-level security does the isolating, so a bug in the application layer still cannot surface someone else’s life.

Retrieval, scarred into shape

Memory recall runs on pgvector embeddings, but pure semantic search earned a scar: during one biography run it missed a friend and a medical scan simply because neither was semantically close to the chapter topic. Retrieval is now two-bucket: one bucket anchored to the topic by keyword and cosine similarity, a second sweeping in every high-relevance memory regardless of similarity, so the biographer never writes around a fact it technically had.

What the AI is allowed to cost

Mnevra used to ask you for your own Anthropic and OpenAI keys. That plan was retired in September 2026 before it ever went on sale, because handing a customer a second, unpredictable bill is not a product. There is now one subscription, NZD 14.99 a month through the App Store, with a 7-day trial that needs no card, and the model spend is mine to manage. So it is measured: every call is costed to the hundredth of a cent, voice is billed per modality because an audio token costs several times what a text one does, and a subscription carries a monthly compute ceiling with rolling five-hour and weekly floors underneath it. Going over that ceiling throttles you. It does not lock you out, and it never touches your data. Whether you may use the product and whether you have spent this month’s compute are two different questions, and the code answers them with two different status codes.

Dogfood, dated and numbered

Mnevra’s primary test subject is my own life. After about 25 weeks of daily use the graph holds 618 memories, 147 people, 130 places and 677 connections between them, across four spaces, and the commit log reads like a diary of being your own user. The notification cadence got retuned from real annoyance. The voice personas got re-cast (Alfred is now a proper British valet). One fix exists purely because Neve re-asked a question I had already answered: the analyser was regenerating a gap under a fresh id and losing the record that it had ever been asked. Everything here improves the same way, by being lived with, daily, until the rough edges file themselves smooth.