Automate Jira + Linear
The ticket system of record for engineering work. Fast issue tracking that deserves fast automation. Put an agent between them and the hand-off stops being manual: it reads, decides, acts, and shows its work.
Meeting Follow-Through already works across Jira and Linear — free, and it runs on your machine.
Automations teams run
These are not field mappings. An agent reads the Jira side, works out what it means, and only then decides what — if anything — should happen in Linear.
When an issue is created or transitions in Jira…
…an agent can create issues with full context in Linear — after reading the context and deciding it should.
When a sprint starts in Jira…
…an agent can update status and assignees in Linear — after reading the context and deciding it should.
When a priority changes in Jira…
…an agent can write cycle summaries in Linear — after reading the context and deciding it should.
When an issue is created in Linear…
…an agent can create and update issues in Jira — with the reasoning recorded in the run’s receipt.
When a status changes in Linear…
…an agent can transition tickets with comments in Jira — with the reasoning recorded in the run’s receipt.
When a cycle ends in Linear…
…an agent can summarise sprint state in Jira — with the reasoning recorded in the run’s receipt.
Copy this Jira → Linear workflow
Concretely: a custom-api call to {yoursite}.atlassian.net on one side, a custom-api call to api.linear.app on the other, and an agent in between that can decline. Deciding not to write into Linear is a recorded outcome, not a silent one.
{
"id": "473c831a-ff5d-4461-a2a9-f6cd24a4d57e",
"name": "Jira → Linear",
"nodes": [
{
"id": "42da5bf2-6cf9-4214-a484-6f8838cfaa80",
"text": "Poll Jira",
"x": 512,
"y": 144,
"isEditing": false,
"type": "trigger-timer",
"icon": "connect",
"category": "trigger",
"isSelected": false,
"parameters": {
"interval": "15",
"unit": "minutes"
},
"description": "Checks Jira on a schedule.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
},
{
"id": "b9e80521-8192-4ce4-a7fc-7db599c03c10",
"text": "Read it and decide",
"x": 512,
"y": 336,
"isEditing": false,
"type": "agnt-agent",
"icon": "connect",
"category": "action",
"isSelected": false,
"parameters": {
"instructions": "Read the Jira item. Decide whether it warrants action in Linear, and explain why."
},
"description": "Decides whether this Jira item warrants anything in Linear.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
},
{
"id": "683dde4c-1de8-4ce8-ac4b-0018e1d21674",
"text": "Call Linear",
"x": 512,
"y": 528,
"isEditing": false,
"type": "custom-api",
"icon": "connect",
"category": "action",
"isSelected": false,
"parameters": {
"url": "https://api.linear.app/graphql",
"method": "POST"
},
"description": "Writes into Linear over its API.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
}
],
"edges": [
{
"id": "2fe60618-fcfa-4b2b-ac49-cf19dfd76266",
"start": {
"id": "42da5bf2-6cf9-4214-a484-6f8838cfaa80",
"type": "output"
},
"end": {
"id": "b9e80521-8192-4ce4-a7fc-7db599c03c10",
"type": "input"
},
"startX": 800,
"startY": 168,
"endX": 512,
"endY": 360
},
{
"id": "b271639e-81ee-4f58-a609-1f429b349bc0",
"start": {
"id": "b9e80521-8192-4ce4-a7fc-7db599c03c10",
"type": "output"
},
"end": {
"id": "683dde4c-1de8-4ce8-ac4b-0018e1d21674",
"type": "input"
},
"startX": 800,
"startY": 360,
"endX": 512,
"endY": 552
}
],
"zoomLevel": 1,
"canvasOffsetX": 0,
"canvasOffsetY": 0,
"isTinyNodeMode": false
}Install Meeting Follow-Through
Meeting Follow-Through already uses both Jira and Linear, so installing it gives you this exact hand-off wired up — connected, editable, and running on your own machine.
Runs on your own machine · See what it does
Build it in AGNT
- Download AGNT Community Core — free and local-first.
- Connect Jira with one OAuth sign-in and Linear with an API key pasted into the vault; both land in the local vault.
- Start from a marketplace workflow, or drop a custom-api node and a custom-api node onto the canvas with an agent between them.
- Put an approval gate on anything consequential, then run it — the receipt shows what was read in Jira and what was written to Linear.
Jira and Linear — common questions
Can I connect Jira to Linear without writing code?
No code is required. Add both connections in the vault (Jira uses one OAuth sign-in, Linear uses an API key pasted into the vault), then either install a marketplace workflow for this pair or drag the two nodes onto the canvas and put an agent between them.
How is this different from a field-mapping Jira to Linear automation?
Mapping tools move data; this reasons about it. Rather than copying a field into Linear, the agent can weigh what arrived from Jira, classify it against criteria you wrote in prose, draft something new, and act only when it is warranted.
Does my Jira and Linear data leave my machine?
Not to us. AGNT runs locally and both sets of credentials are encrypted on your own disk. Outbound traffic goes only to Jira, Linear and whichever model you chose — and pointing that at Ollama or LM Studio keeps everything on your hardware.
What does a Jira and Linear run leave behind?
A receipt: what was read in Jira, which tools ran with which arguments, what the agent concluded, and what it wrote to Linear. Anything consequential can sit behind an approval gate so a person signs off before it happens.
