My Alicia

Most AI tools are built for everyone. My Alicia is an AI teammate built for me.

What she says and why she says it is private. It's based on what I read, the notes I take, the questions I ask. But how she works and how she grows is yours to take and adapt however you want. My Alicia can be Your [Name].

Three depths of attention

She runs on three loops at three timescales. She listens in the moment. She notices over hours. And she comes to know over days and weeks. The slower loops watch the faster ones, so patterns surface on their own.

The three relationship loops of myalicia Listen, Notice, and Know — three depths of attention that compound over time, sharing a memory substrate, reachable through Telegram and Claude Code surfaces. Memory vault · notes · archetype Listen seconds · be present Notice minutes–hours · catch patterns Know days–weeks · come to know conversation event-triggered synthesis scheduled reflection Telegram conversational Claude Code technical an AI teammate that grows into the shape of the person it serves

Three depths of attention — Listen, Notice, Know — over a shared memory substrate.

From notes to wisdom

Knowledge moves through her in altitudes. Daily inputs metabolize into synthesis. Synthesis metabolizes into wisdom. External research keeps the loop open to new authors and viewpoints, so she doesn't only reflect what's already in the vault.

Knowledge altitudes Three altitudes of knowledge — inputs at the bottom, synthesis in the middle, wisdom at the top. Knowledge compounds upward. External research feeds into synthesis from outside. WISDOM deep topics · provocations · drawings · insights SYNTHESIS patterns · connections · weekly summaries · bridges INPUTS notes · quotes · voice feedback · conversations external research new authors new viewpoints Knowledge compounds upward. External research keeps the loop open.

From notes to wisdom — the altitudes of knowing.

For designers and builders

The contribution surface is what we call awareness primitives — small, opinionated modules that turn some slice of life into structured memory the loops can metabolize: a reading-pattern primitive, a calendar-rhythm primitive, a relationship-graph primitive.

Think of contributions as designing perception. That's what design practice needs to expand into in the agentic era.

Try it

pip install myalicia && myalicia init

The init flow is more than configuration — it's a guided introduction to relationship-shaped AI. Each setup step is paired with a one-screen explanation of which loop it activates and why.

View on GitHub →