We built a desktop app that screenshots your screen periodically, runs it through a vision model, and stores the context locally. Then it pipes everything into your AI tools via MCP.
Most people we showed it to started using it to generate timesheets.
Any ideas for what else this could do are welcome!
Website: https://trymemorylane.com/
GitHub: https://github.com/deusXmachina-dev/memorylane
reply