Journalists

Your source Rolodex that never leaks.

Journalist source Rolodex: a single EU-hosted encrypted archive, AI-queryable, never leaks to US chatbots

Reporters accumulate thousands of sources, transcripts, briefings and background notes across a career. They live on laptops, on paper, in old Evernote accounts, in Signal threads. BrainCopy pulls them into one EU-hosted, encrypted archive your AI assistant can query — without sending a single byte of source material to a US chatbot.

The problem

Five years into a beat you have a network of a thousand contacts, a hundred interview transcripts, and a dozen notebooks of margin reporting. Finding a specific quote from 2022 is a two-hour excavation, and you're not the only one who's taken notes — an editor, a producer, maybe a fact-checker each has fragments.

The modern note-taking stack — Notion, Evernote, Google Docs, iCloud Notes — is all on US infrastructure, none of it end-to-end encrypted against the platform itself, and increasingly entangled with AI training that your sources did not consent to. This is not just a GDPR issue; it's an operational security issue.

Your AI assistant would be transformative for reporting — "every source who mentioned X across my archive" — but you can't feed source material to a US chatbot without breaking trust and possibly breaking law, depending on jurisdiction.

How BrainCopy solves it

Everything in one EU-hosted archive

Import Evernote, Notion, Apple Notes, Google Docs exports, Signal archives, old laptop folders. BrainCopy stores them on Hetzner Germany, per-user encrypted, under Swedish-company data governance. One searchable corpus, off US infrastructure.

Every source becomes a dossier

Each source in your people graph accumulates every mention, every interview, every call log, every document shared. Years of reporting on one person becomes a continuous file, not a search-across-twelve-tools exercise.

OCR your reporter's notebooks

Claude-based OCR handles reporter shorthand and the margin-of-a-page kind of writing. Uncertainty is flagged, not guessed — you can cross-check against the recording if you kept one. Decades of paper reporting become full-text searchable.

Private AI, via your own MCP endpoint

Claude or ChatGPT connects to your BrainCopy as an MCP tool. "Every source who mentioned a specific shell company across three years" returns a list with citations. The AI queries your archive but doesn't upload wholesale content to the model provider; you can also run entirely local AI if you prefer.

Source-protection features built in

Tag sources as "sensitive" — these are excluded from AI responses by default, from exports by default, and require explicit per-source opt-in for any sharing. Audit log of every access. One-click "scrub this source" for subject access requests or legal risk moments.

What you'll actually see

Beta price for Journalists

50% off the €10/month subscription, forever, for working journalists. Your discount never expires.

PRESS50

Start with PRESS50 See full pricing

FAQ

Is my source material safe?
EU hosting (Germany), encrypted-at-rest, zero-retention AI processing, sensitive-source tagging with strict default access. Your raw files live on a Nextcloud account under your own control — you have direct sync-client access independent of BrainCopy. If we disappeared tomorrow, you'd keep everything.
Can I use this for off-the-record material?
Yes — tag as sensitive and such items are excluded from AI responses, from exports, and from any automated surface. Explicit opt-in for any sharing. This is designed for exactly this use case.
What about subpoena / legal compulsion?
BrainCopy is based in Sweden with EU hosting — you're protected by Swedish and EU press-freedom frameworks, not US ones. We publish our legal-request policy, and sensitive-tagged data has additional internal restrictions. End of the day, any third-party storage has some legal exposure; many journalists mitigate with a second-layer encryption on highest-sensitivity material.
How's this different from Evernote / Obsidian / Notion?
They're editing and filing tools; BrainCopy is a cross-platform archive + people graph + AI-queryable surface. You can keep using Obsidian for drafting and BrainCopy as the source-layer underneath. Many journalists do exactly that.
Cost?
€10/month (€5/month forever with PRESS50). One-time OCR + import of a decade of notebooks is typically €100–€400. Expensable as a professional tool in most jurisdictions.
Can my editor or producer have access?
Yes — per-tag access controls. Share "story A" with an editor, keep "sources for story B" scoped to you. Full multi-user collaboration is on the roadmap.
What about AI hallucinations?
MCP returns actual text from your archive with citations to the source record. Hallucination risk drops dramatically compared to feeding a summary into a chatbot — the AI is retrieving, not reconstructing.

Ready to try it?

Takes about 30 seconds to sign up. You can start importing immediately.

Start your reporter trial

Who else uses BrainCopy

Different people, same problem: too many memories scattered across too many places.