Afterimage: Turning Your Digital Footprints into AI-Powered Daily Reflections, AI-Gen
Your computer knows what you did. But can it help you understand how you worked? The Problem We spend hours every day in front of our computers. Our applications record activity. Our operating systems track processes. Our calendars store schedules. Yet, at the end of the day, it is surprisingly dif
Hacktoberfest Open-Source AI Challenge: Ghost in the Machine Submission 馃懟馃尲
Your computer knows what you did. But can it help you understand how you worked?
We spend hours every day in front of our computers.
Our applications record activity. Our operating systems track processes. Our calendars store schedules.
Yet, at the end of the day, it is surprisingly difficult to answer some simple questions:
Traditional time trackers provide numbers: application names, durations, and activity logs.
But numbers alone rarely provide useful reflection.
I wanted to build something that could turn these digital traces into a meaningful record of my working day.
Afterimage is a native desktop activity tracking and AI-powered retrospective system for Linux, designed for KDE Plasma 6 on Wayland.
It collects lightweight activity signals from the desktop, organizes them into work sessions, and uses Large Language Models (LLMs) to generate daily reflections.
"What happened during my working day, and what can I learn from it?"
Repository: https://github.com/lyf266/Afterimage
Afterimage is organized into four main stages.
Afterimage uses native KDE KWin scripting and Linux input-event monitoring to collect activity signals.
It does not record actual keystrokes or mouse coordinates.
The goal is to understand activity patterns without collecting the content of everything you type.
Raw activity events are not particularly useful on their own.
Afterimage aggregates them into sessions and calculates indicators such as:
These are heuristic indicators based on observable desktop activity, not scientifically validated measurements of productivity or mental states.
The system supports multiple LLM providers:
The default configuration uses local Ollama with Qwen2.5:7b.
The AI receives structured activity summaries and generates a human-readable retrospective, helping identify major work sessions, possible distractions, and patterns worth reviewing.
The system also supports natural-language queries over historical activity.
afterimage ask "What was I mainly working on last Wednesday afternoon?"
The final result is not locked inside a dashboard.
Afterimage can generate Markdown reports and save them locally.
It also supports integration with personal knowledge-management workflows such as Obsidian and Logseq.
This makes daily activity records easier to review, search, and connect with longer-term goals.
Here is an example of the kind of retrospective Afterimage can produce:
The objective is not to let AI judge whether someone had a productive day.
It is to provide a structured starting point for personal reflection.
Afterimage is designed with local-first operation in mind.
Cloud providers are also supported, but using them means sending the relevant sanitized data to an external API.
Sanitization is a protective layer, not a guarantee that all personal information will be removed. Users should review their configuration before enabling cloud inference.
I think personal AI tools should give users control over how their data is processed.
For this kind of application, local inference offers several advantages:
Open-source software combined with locally runnable AI makes it possible to build personal tools that would otherwise require sending large amounts of behavioral data to third-party services.
The project also includes a command-line interface, systemd integration, installation scripts, and automated tests.
Building Afterimage made me think differently about personal productivity software.
The difficult part is not simply collecting more data.
It is deciding which signals are useful, how to organize them, how to protect private information, and how to turn raw activity into something a person can actually reflect on.
AI is useful here not because it can magically measure productivity, but because it can help interpret structured information and turn it into a readable narrative.
GitHub: https://github.com/lyf266/Afterimage
Afterimage is currently designed for Linux users running KDE Plasma 6 on Wayland.
The repository includes installation instructions, configuration examples, tests, and usage documentation.
If you are interested in local AI, personal knowledge systems, desktop telemetry, or privacy-conscious productivity tools, contributions and feedback are welcome.
What would you want your computer to remember about your working day?