/ connectors · Linear
Connect Linear to Mari
Linear is where the product decisions happen now. The spec lives in an issue, the debate lives in its comments, and the resolution ships before anyone writes it up anywhere else. Which is fine, until someone asks "why did we build it this way?" eight months later.
Mari's Linear connector keeps that reasoning retrievable.
What syncs
- Issues, specs, and discussion from your Linear workspace, fetched through Linear's GraphQL API, each becoming a searchable knowledge document.
- Incremental sync through Mari's one pipeline: chunk, content-hash, embed. Unchanged issues are never re-embedded, so a routine resync costs seconds.
Connecting takes a minute
Create a personal API key in Linear (Settings, then Security & access), paste it (lin_api_...) into Mari's connector form, and hit Test connection: a wrong key shows Linear's actual error, verbatim. Connect, and a scheduled sync flow keeps the workspace fresh from then on.
What you get back
Ask "why did we build it this way?" and the answer streams with numbered citations back to the exact issue and its discussion. Linear content ranks alongside your repos, Slack threads, and wikis in one hybrid search. And the decisions worth keeping can graduate into Mari's decision ledger: proposed, ratified, superseded, with the trail attached.
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 workspace never leaves your deployment.
Start here
- Quick start:
docker compose upto a working knowledge base. - The docs cover connecting a source step by step.
- Book a demo to see it live.
Also connects: GitHub, Slack, Jira, Notion, Zendesk, and more. 12 connectors, one pipeline.