/ connectors · Confluence

Connect Confluence to Mari

Every Confluence space has two kinds of pages: the ones people trust and the ones people have learned to ignore. The wiki doesn't tell you which is which. A page written three reorgs ago looks exactly like one updated yesterday, and the search box treats them the same.

Mari's Confluence connector pulls your spaces into a knowledge base that holds every page accountable.

What syncs

• Pages from a Confluence Cloud space, selected by space key, through Atlassian's REST API.
• Incremental sync through Mari's one ingestion pipeline: chunk, content-hash, embed. Unchanged pages are never re-embedded, so a routine resync costs seconds.

Connecting takes a minute

Pick Confluence from the connector list and fill three fields: your site URL (yourco.atlassian.net), the email on the account, and an Atlassian API token. Test connection surfaces Atlassian's real error if something's off, verbatim. Connect, and a scheduled sync flow keeps the space fresh from then on.

What you get back

Ask a question and the answer streams with numbered citations back to the exact page. Confluence pages rank alongside Slack threads, repo commits, and tickets in one hybrid search. Then the accountability layer does what the wiki can't. Claims from pages become facts with owners and verification states, and the repo audit flags documentation drift when the code moves on from what a page says.

Where a wiki stops at "here's the page," Mari carries on to "and here's whether to believe it."

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 wiki never leaves 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: Slack, Notion, Jira, GitHub, Google Drive, Zendesk, and more. 12 connectors, one pipeline.