The Fleece AI Brain Linear connector syncs the issues from your connected Linear workspace into a local-first knowledge base — plain Markdown and SQLite on your own machine. Each issue's identifier, title and description become a note titled by its key, and any MCP-compatible app such as Claude Desktop or Cursor can answer from your real Linear history, with the source one click away.
What syncs from Linear
Everything arrives as knowledge nodes — ordinary files you can open, link and search, not rows behind a workspace login.
Issues
Every issue from your connected Linear workspace that falls in the sync window, pulled through Linear's GraphQL API.
Identifier, title & description
The human key and title become the note title "ENG-123: Fix the thing"; the description becomes the body, so the ticket reads the same in your brain as in Linear.
Issue link
The issue's Linear URL is appended to the body, so the live ticket is always one click from the note.
Workspace tags
Each note is tagged linear and issue/<IDENT> (for example issue/ENG-123), so you can filter your brain down to a single ticket or its whole prefix.
Incremental sync
Runs resume from a stored cursor — the newest updatedAt seen — via an updatedAt >= filter; the first sync backfills the last 90 days rather than the whole workspace history.
Update-in-place & dedup
Keyed on the issue id, an edited issue refreshes its note in place rather than duplicating, and a re-sync never creates a second copy.
Connect Linear in four steps
No workspace admin project, no webhooks — one sign-in from the desktop app.
- 01
Install Fleece AI Brain
Download the desktop app for macOS, Windows or Linux and open your vault — a folder of plain Markdown files on your machine.
- 02
Open Connectors and pick Linear
In the app, open the connectors panel, choose Linear, and sign in with your workspace account. OAuth is brokered securely; your Linear content never passes through our servers.
- 03
Let the first sync backfill
The connector pulls the issues updated in the last 90 days, then keeps pace with everything newer. There is nothing to configure — it reads what your token can see.
- 04
Point your coding agents at it
Connect the Brain to Claude Desktop, Cursor or the agents you build with one copy-paste, then ask why a cycle shipped the way it did — answered from the real issue.
The tickets close. The reasoning leaves with the cycle.
Linear is built for velocity, and it delivers it — issues move from Triage to Done, cycles roll over, and the team keeps shipping. But the argument that shaped a ticket, the constraint that killed an approach, the reason a scope got cut — that context lives in a description and a few comments, then scrolls out of reach as the next cycle fills the board.
The Linear connector keeps it. Every issue becomes a permanent note in one living knowledge graph, linked to the people, projects and tools it mentions — so the decision made in a March cycle is still one question away when someone reopens the area in December.
Your issues go from Linear to your disk. Nowhere else.
Authentication is a standard OAuth sign-in, but the sync calls the Linear GraphQL API from the desktop app on your machine. Whether the token is used directly or brokered, raw issue payloads never transit Fleece's servers — they land straight in your vault as Markdown and SQLite.
That is the whole trust model: we cannot read your Linear workspace. The files are yours, they open in Obsidian or any editor, and if you ever leave, you take every issue with you.
- +Raw issue payloads never transit Fleece's servers
- +Vault = plain .md files + SQLite, 100% Obsidian-compatible
- +Works offline once synced; cloud sync is optional and end-to-end encrypted
Give every coding agent your project's context.
One copy-paste connects the Brain to Claude Desktop, Cursor, Cline, Zed or the agents you build. From then on, an agent about to touch a feature can read the issue that defined it — the constraint, the rejected approach, the acceptance criteria — instead of guessing from the current code.
Because every agent and tool reads the same graph, hybrid search (meaning and exact words, locally) returns the right issue whether you remember its key or only what it was about. On Teams, the organization map also shows which agents used that context and what they cost.
Linear connector — FAQ
Does my Linear data pass through Fleece's servers?+
No. Sign-in uses a brokered OAuth flow, but the sync itself calls the Linear GraphQL API from the desktop app on your machine. Whether your token is used directly or through the broker, raw issue payloads never transit Fleece's servers — they land straight in your local vault.
Which issues does the connector sync, and can I limit it?+
Every issue your connected Linear workspace exposes to your token that falls in the sync window. The first run backfills the last 90 days; after that it keeps pace with newer changes. Scope follows your Linear access — the connector only reads what your account can already see.
Does it write anything back to Linear?+
No. The connector is read-only: it pulls issues into your knowledge base and never creates, edits, comments on or closes anything in your workspace.
How often does it sync?+
Sync runs in the background from the desktop app and resumes incrementally from the newest updatedAt it has seen, so each run only re-examines recently touched issues. An edited issue refreshes its note in place, and re-syncs never create duplicates.
Which plan do I need to connect Linear?+
The local brain is free, and connectors are the paid lever: Solo (€12/month) includes up to 3 connected tools, Pro (€24/month) makes them unlimited with auto-sync. Every plan starts with a 14-day trial, no card required.
How do I ask Claude or my coding agents about Linear?+
Connect the Brain to Claude Desktop, Cursor or any MCP-compatible app with a single copy-paste. Your AI then answers from the synced Linear knowledge, citing the exact issue note it drew from.
Can I open the synced issues outside the app?+
Yes. Every issue is an ordinary Markdown file in your vault, fully Obsidian-compatible — open, edit or grep them with any tool, and take them with you if you ever leave.
What happens if I disconnect Linear?+
Sync stops, and everything already in your vault stays yours — the notes are local files, not a mirror that vanishes with the connection.
Stop losing the why to the next cycle.
Connect Linear in one sign-in and give every coding agent a permanent memory of the reasoning behind your project.