Crawl websites, upload files, pull integrations, and track every ingestion job.
Larkup gives you one Data page for every source. Add content once, and Larkup indexes it in the background.
The Data page, with a tab for every source
Website
Files
Text
Media
Integrations
Search by keyword or paste a direct URL. The built in local crawler works immediately; switch to the Cloud web crawler in Settings for JavaScript heavy or protected sites.
Starting a crawl by keyword
Jobs run in the background. Track pages processed and status right in the tab.
A running crawl job
Drop in PDF, Word, CSV, JSON, Excel, or plain text. Structured files get a column and schema preview before you confirm.
Files staged with a schema preview
Paste notes, transcripts, or any text you want to search, with a title.
Adding raw text directly
Upload images, video, or audio, or paste a YouTube URL. Install the Video Intelligence marketplace tool for transcription and frame analysis. See Chat with Video.
Importing a video from a URL
Connect Notion, Google Drive, Slack, Jira, and more. Choose Configure or Connect, authorize through OAuth or an API key, and Larkup pulls the content in and indexes it.
Available integrations
Service
Category
What gets indexed
Notion
Documentation
Pages, databases, and knowledge bases
Google Drive
Documentation
Files and shared drives
Slack
Communication
Channels, messages, and DMs
Confluence
Documentation
Pages, spaces, and knowledge bases
Jira
Project management
Issues, sprints, and projects
Linear
Project management
Issues, projects, and roadmaps
GitHub
Engineering
Repositories and README knowledge
Salesforce
CRM
Accounts, contacts, and opportunities
Don’t see what you need? Select Ask for integration. Sync again anytime to pull fresh content.
Configure the web scraper and web search provider under Settings → Search & Scraping. No .env editing required.
Search & Scraping settings
Prefer hosted crawling? Add a Firecrawl or Serper.dev API key here instead of running the local crawler. Organizations that route traffic through a proxy can set it here too.
