Inspiration
Documenting harassment or abuse is often overwhelming, especially when evidence is scattered across messages, screenshots, and online links. Many existing tools either compromise privacy or are too complex to use during stressful moments. Archivum was inspired by the need for a simple, privacy-first way to help individuals organize their experiences without requiring trust in external storage or platforms.
What it does
Archivum allows users to securely collect and organize evidence related to harassment, abuse, or misconduct. Users can upload screenshots, add links, paste messages, and create a chronological timeline of events. The application then generates a structured incident documentation PDF using AI, helping users present their experiences clearly and factually.
How we built it
Archivum was built as a fully client-side web application using HTML and CSS for layout and responsive design, and vanilla JavaScript for interactivity and state management. jsPDF is used for client-side PDF generation, while the Google Gemini API assists in generating structured incident documentation. All evidence is handled locally in the browser, and no backend server is used.
Challenges we ran into
One major challenge was balancing AI functionality with privacy. Ensuring that evidence remained local while still generating meaningful AI-written documentation required careful handling of data and prompts. Another challenge was managing large images and formatting long AI-generated text correctly across multiple PDF pages without breaking layout or readability. ALso
Accomplishments that we're proud of
We are proud of building a fully functional, privacy-first evidence documentation tool entirely on the client side. Successfully generating structured, readable PDFs in the browser and integrating AI in a responsible, non-exaggerated manner were major milestones. Completing the project without relying on a backend server was also a significant achievement.
What we learned
Through this project, we learned how to design AI-assisted tools responsibly for sensitive use cases. We gained experience with client-side file handling, PDF generation, prompt engineering, and designing user interfaces for emotionally challenging scenarios where clarity and simplicity matter.
What's next for Archivum
Future plans for Archivum include adding optional local encryption, allowing users to provide their own API keys, improving accessibility, and supporting case export and import features. With further development, Archivum could become a trusted tool for safe, ethical documentation and personal record-keeping.
Log in or sign up for Devpost to join the conversation.