Second brainMy own system · runs every day
Twenty years of messages. I ask them in plain words.
Telegram, email, notes, calendar, Drive, meeting recordings and AI sessions flow into one base. It updates every two hours, and profiles of people and projects build themselves.
Built it myself: source collectors, a base with search by meaning, relationship graphs, profiles, a morning briefing and a Telegram bot.
One question, two ways to find the answer
Example on demo data- Try to remember where it came up: a chat, an email or a call
- Scroll through six months of messages
- Piece the decision together from three places
I ask out loud, the way I'd ask a person: "what did we agree with the contractor?" The answer has the decision, what's still open, and links to the meeting and the chat it came from.
How the base finds an answer
People, projects, meetings and emails are linked in a graph. A question about a person walks through their links: deals, recent chats, meetings, decisions. The answer draws on several sources at once.
Chats, emails and notes go into the base as is, read-only. Everything derived lives in a separate layer: profiles, indexes, a dashboard. A synthesis error never touches the source.
Every source has a date. If a profile is from spring but everything changed in a chat yesterday, the answer goes with yesterday and says plainly where the base disagrees.
What runs every day
New chats, emails, notes and meetings land in the base on their own.
Meetings, urgent tasks and stuck projects, from real data only.
For people and projects: history, status and open questions.
Ask by voice or text from anywhere, get a plain-text answer.
Finds a note even when you no longer remember the exact words.
The base lives on my own server, not in someone else's cloud.
