Integration Tutorial April 13, 2026

Import Jira Issues as AI Knowledge

Every Jira ticket is a decision record -- why something was built, what broke, who fixed it. REM Labs imports your Jira history so AI can search across every issue, epic, and sprint comment by meaning. Stop digging through JQL when you can just ask.

What Gets Imported

The Jira integration extracts structured data from each issue and stores it as a richly typed memory:

Summary and description -- the full issue body, converted from Jira markup to clean text
Comments -- every comment on the issue is captured with author and timestamp
Fields -- status, priority, assignee, reporter, labels, components, sprint, epic, story points -- all stored as filterable metadata
Issue links -- "blocks", "is blocked by", "relates to" relationships become knowledge graph edges
Attachments -- text extracted from attached documents and images (with OCR)

Connect Your Jira Instance

In the REM Labs Console, go to Integrations and click Connect Jira. Authorize via Atlassian OAuth 2.0 and select the projects to sync. You can scope to specific projects or import your entire instance.

Import via API

curl -X POST https://api.remlabs.ai/v1/memory/sync/jira/import \
  -H "Authorization: Bearer sk-slop-..." \
  -H "Content-Type: application/json" \
  -d '{
  "jira_url": "https://yourteam.atlassian.net",
  "jira_token": "ATATT3xFf...",
  "jira_email": "dev@company.com",
  "projects": ["ENG", "INFRA", "MOBILE"],
  "include_comments": true,
  "issue_types": ["Story", "Bug", "Task", "Epic"],
  "sync_mode": "incremental"
}'

The issue_types filter lets you skip sub-tasks or other issue types you do not need. Incremental mode uses the updated field to only process issues modified since the last sync.

JQL-Scoped Import

For targeted imports, pass a JQL query to sync only matching issues. This is useful for importing a specific epic, sprint, or time range.

curl -X POST https://api.remlabs.ai/v1/memory/sync/jira/import \
  -H "Authorization: Bearer sk-slop-..." \
  -H "Content-Type: application/json" \
  -d '{
  "jira_url": "https://yourteam.atlassian.net",
  "jira_token": "ATATT3xFf...",
  "jira_email": "dev@company.com",
  "jql": "project = ENG AND sprint in openSprints()",
  "include_comments": true
}'

Search Your Issue History

curl -X POST https://api.remlabs.ai/v1/integrations/jira/search \
  -H "Authorization: Bearer sk-slop-..." \
  -H "Content-Type: application/json" \
  -d '{
  "query": "authentication timeout errors in mobile app",
  "filters": {"project": "MOBILE", "status": "Done"},
  "limit": 10
}'

Semantic search finds the bug report titled "Token refresh race condition on iOS" and the story "Implement session keepalive" -- neither of which mentions "timeout" literally, but both are relevant to your query.

API Endpoints Reference

Endpoint	Method	Description
`/v1/memory/sync/jira/import`	POST	Import issues from Jira projects or JQL
`/v1/integrations/jira/status`	GET	Check sync status per project
`/v1/integrations/jira/search`	POST	Search within the Jira namespace
`/v1/integrations/jira/webhook`	POST	Configure real-time issue sync webhook

Issue links as graph edges: Jira's "blocks", "is blocked by", and "relates to" links are stored as edges in the REM knowledge graph. When you search for a topic, related issues discovered through link traversal appear in results. See Jira integration docs.

Turn your Jira history into AI memory

Free tier. Semantic search across every ticket ever filed.

Get started free →