DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to turn receipt photos into searchable table records with Kition

Drop receipt images into an attachment field and let vision-powered fields fill in vendor, category, and text.

Credentials. Receipts can show account numbers, addresses, and personal purchase details, so check what the AI fields send to your configured model before you upload them.

Who it is forA freelancer, small business owner, or household admin who keeps a pile of receipt photos for expense tracking.

The problemTyping receipt details by hand takes time, and photos in a folder cannot be filtered or summarized.

The outcomeA table where each receipt row holds its image, vendor, address, category, structured JSON, and OCR text, ready to filter and summarize.

What you need first

  • A macOS, Windows, or Linux (experimental x86_64) computer to install the desktop app from GitHub Releases
  • A model or account setup inside Kition for the Agent and AI fields (the README mentions model and account settings but does not detail the providers)
  • For source builds only: Node.js 22.19.0, pnpm 10.33.0, Rust (stable), and the Tauri system prerequisites for your platform
  • Back up important workspaces before relying on the beta app

Steps

  1. Download and install the Kition desktop build from GitHub Releases.
  2. Create a table file with an attachment field and AI fields for vendor, address, category, structured JSON, and OCR text.
  3. Drop the receipt photos into the attachment field, one receipt per row.
  4. Check the extracted values in each row and correct any mistakes.
  5. Use table filters or ask the Agent to summarize the corrected rows.

Prompt for your agent

In the Kition desktop app, open the table <table name> that has receipt attachments and AI extraction fields. Ask the Agent to total the category values for the rows marked <month>, and check that each total matches the corrected rows before you use it.

Caveat. The README describes vision-powered fields but does not name the model providers or accuracy, so verify extracted values before relying on them.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page