existence-trace is an open-source CLI (etrace) for an AI that reads your journal every day, asks you where it is unsure, turns your answers into rules, and has to prove it used them. It runs on your own files with any model, under the MIT license.

The problem

You spend hours a week with Claude, ChatGPT or Codex. They learn your stack, your repo and your naming style. What they pick up about you ends up in a vendor's memory you cannot fully check, or nowhere at all. existence-trace is the missing half: a journal your AI actually reads, in files you own.

How it works

  • You write. A few lines a day, or import old diary files (.md, .txt, Day One .json) with one command.
  • It reads. Each day it writes a report through three lenses: emotion (PAD), stability and exploration (G), growth (XP).
  • It asks. When it is unsure about you, it asks one question with evidence instead of guessing.
  • It proves. Your answer becomes a rule. When a rule changes a report, it records a receipt with the before and the after. A weekly audit fails if a rule was never applied.

Your own words stay word for word in a protected block that nothing can rewrite; the AI only writes its own blocks. PAD, G and XP are reflection aids, not clinical scales.

Compared with built-in chat memory

Built-in chat memory existence-trace
Where it lives the vendor's account plain text files in your own folder, versioned with git
Who decides what is remembered mostly the model you: it asks, you answer, the answer becomes a versioned rule
Proof it used what it knows none a receipt with before and after, and a weekly audit
Which AI one vendor Anthropic, OpenAI, DeepSeek, OpenRouter, Ollama, or any OpenAI-compatible address

Try it

It needs Python 3.11+ and uses the standard library only.

curl -fsSL https://maxont.github.io/existence-trace/install.sh | bash etrace ai set # connect an AI etrace import ~/Documents/diary --run # bring in your old diary and let the AI read it 

Add --dry-run to the installer or to etrace import to preview first. With no old diary, run etrace init, then etrace note to open today's page and etrace run daily to read it. Your AI key is kept outside your data folder.

Where it fits

existence-trace is about one person's own record. Its sibling projects are about agents. aisync handles Multi-Agent Context Management, Coordination & Observability across AI coding tools, and TRACES.md is a format for recording what each agent did. They are separate repos; existence-trace does not depend on either.

Limits

This is a young project and the numbers it reports are reflection aids, not measurements. It is not a clinical or therapy tool. It sends your journal text to whichever AI service you connect, so choose one you are comfortable with, or use a local model through Ollama.