Airparser vs Stalwart mail-parser

Airparser turns emails, PDFs, and other documents into structured fields you define. Its text and vision language models plus AI OCR handle typed text, scans, and handwriting, with recognition in more than 60 languages. Low-confidence results can wait for human review, correction, and approval before export. Parsed information can be downloaded as Excel, CSV, or JSON, or sent to webhooks and services including Zapier, Make, n8n, Google Sheets, and Airtable. Python post-processing is included in plans, and an AI code assistant can draft and test code from plain-language instructions. Airparser works through the web and an API, with workflow routing and cloud deployment. Each parsed email, document, or PDF page consumes one credit, and unused credits expire at the billing period’s end. A Trial plan is listed at free with 20 credits/month and 30 days’ retention. Paid plans start at $33 a month, billed annually.

Stalwart mail-parser is a free, open-source Rust library for parsing email messages. It supports Internet Message Format RFC 5322, MIME RFC 2045–2049 and other internet messaging RFCs, while attempting to handle messages that depart moderately from those standards. Parsed output includes a MIME tree, text and HTML body lists, and attachments. If one alternative is missing, the library can convert HTML to plain text or plain text to HTML. SIMD kernels accelerate scanning on supported targets, while transfer decoding and charset conversion wait until content is read. Returned strings generally reference the original input message. WHATWG encoding labels are recognized, and the optional full_encoding feature adds legacy multibyte sets including Shift_JIS, Big5 and GB18030. Defaults allow nesting depth 64, 10,000 MIME parts and three decoded nested-message levels. Rust 1.98 is required. No feature is enabled by default; serde adds serialization. The library is licensed under MIT or Apache-2.0 and costs nothing.