/ connectors · Dropbox

Connect Dropbox to Mari

Dropbox folders accumulate the writing that never found a better home: the Paper docs from planning cycles past, the READMEs that predate the wiki, the notes folder someone keeps religiously. It's knowledge, and it's invisible.

Mari's Dropbox connector indexes it where your team actually searches.

What syncs

• Markdown, text, and Paper docs from a folder you choose, recursively. Files over 1 MB are skipped, which for text files is a generous ceiling.
• Incremental sync on Dropbox's own cursor. The connector uses Dropbox's native change cursor, so a resync fetches exactly what changed and nothing else. Mari's pipeline (chunk, content-hash, embed) never re-embeds what didn't.

Connecting takes a minute

Paste a Dropbox access token (sl....), optionally point at one folder path (/notes), and hit Test connection: a wrong token shows Dropbox's actual error, verbatim. Connect, and a scheduled sync flow keeps the folder fresh from then on.

What you get back

Ask a question and the answer streams with numbered citations back to the exact file. Dropbox docs rank alongside your repos, Slack threads, and wikis in one hybrid search, so the notes folder finally pulls its weight.

Runs on your infrastructure

Mari is self-hosted and Apache 2.0. Postgres with pgvector is the whole data plane, models run locally through ollama, and every LLM feature has a deterministic fallback. Your files never leave your deployment.

Start here

• Quick start: docker compose up to a working knowledge base.
• The docs cover connecting a source step by step.
• Book a demo to see it live.

Also connects: Google Drive, Notion, Confluence, Slack, GitHub, and more. 12 connectors, one pipeline.