{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiflmsobws2bn4rbl7fk3w4el6mhtijhqh43bmfqvznwc4thozdlqq",
    "uri": "at://did:plc:mz7h4r2iyp2egghuqaolnsev/app.bsky.feed.post/3mj42tlx7c5n2"
  },
  "path": "/forum/app-development-programming/introducing-my-app-chronicle-visually-intelligent-document-reader",
  "publishedAt": "2026-04-09T09:12:01.000Z",
  "site": "https://applevis.com",
  "tags": [
    "https://github.com/harry6116/Chronicle",
    "https://github.com/harry6116/Chronicle/releases/tag/v1.0.0",
    "https://github.com/harry6116/Chronicle/releases/download/v1.0.0/Chronicle.1.0.mac.zip",
    "https://github.com/harry6116/Chronicle/releases/download/v1.0.0/Chronicle.1.0.windows.zip",
    "https://github.com/harry6116/Chronicle/issues"
  ],
  "textContent": "Hello to you all,\nI want to tell you a bit about an app that I have designed for the Mac and windows to help out in those situations where standard OCR just does not hit the mark.\nChronicle\n\nChronicle is an accessibility-first desktop app for recovering difficult documents.\n\nI built it because ordinary OCR kept failing on material I cared deeply about, especially the First World War diaries of the Manchester Regiment, where my great-grandfather Albert Henry Wharton served after lying about his age to join the British Army at just 15 years old.\n\nI was not trying to make a generic OCR experiment. I was trying to read difficult historical material properly and follow a real human story through damaged, messy, often barely usable source documents. The same problem kept showing up in old newspapers and other archival material too. Things that looked legible in theory were still unreadable in practice.\n\nThat is why I built Chronicle: to make ugly, degraded, awkward documents more readable, more reviewable, and more accessible.\n\nEven when I asked other people to help read some of the war material to me, the problem did not go away. Certain pages were so faded and difficult that even sighted people I asked to help could not read them with confidence. That mattered to me. It meant this was not just a matter of software performing badly; it was an access problem as well.\n\nChronicle was vibe-coded, but all prompting, testing, tuning, sculpting, and final integration were directed by me. It was shaped through repeated testing across many thousands of pages, run again and again so each prompt could be refined until it behaved as intended on difficult real-world material.\n\nWhat Chronicle is especially good at:\n\n- degraded scans\n- archival records and historical documents\n- long-form books and memoirs\n- newspapers and multi-column layouts\n- handwriting, forms, manuals, and mixed-format batches\n- output that is easier to review in HTML or Word rather than just dumping raw OCR text\n\nChronicle also uses document presets so different kinds of material are not all forced through the same blunt workflow. Some of the main preset families include:\n\n- Miscellaneous / Mixed Files\n- Letters / Correspondence\n- Government Reports / Records\n- Legal / Contracts / Laws\n- Books / Novels\n- Newspapers\n- Handwritten Letters / Notes / Diaries\n\nChronicle supports multiple AI providers, including Google Gemini, Anthropic Claude, and OpenAI, and it can export to HTML, TXT, DOCX, Markdown, PDF, JSON, CSV, and EPUB.\n\nSome of the key workflow features include:\n\n- seamless merge mode for combining many pages, scans, or source files into one continuous output\n- queue-first processing with pause, resume, and stop controls\n- page or slide scope controls for PDFs and slide decks\n- automatic engine routing, with manual engine override if you want to force a provider or model\n- scanner and NAPS2 import support\n- session recovery after interrupted runs\n- collision controls so outputs can be skipped, overwritten, or auto-numbered\n- original page-number preservation when source tracking matters\n- controls for punctuation, abbreviations, units, currency, and image descriptions\n- visible in-progress temp files during long runs\n\nFor advanced users, Chronicle also includes more detailed controls in Preferences, including custom prompt additions and other fine-tuning options for shaping behavior more deliberately.\n\nRepository:\nhttps://github.com/harry6116/Chronicle\n\nRelease page:\nhttps://github.com/harry6116/Chronicle/releases/tag/v1.0.0\n\nDirect downloads:\nMac: https://github.com/harry6116/Chronicle/releases/download/v1.0.0/Chronicle.1.0.mac.zip\nWindows: https://github.com/harry6116/Chronicle/releases/download/v1.0.0/Chronicle.1.0.windows.zip\n\nIf you are looking for the direct download links on the repository page, check the README \"Download Chronicle\" section or open the GitHub release page and look under the release assets.\n\nImportant boundary:\n\nChronicle stores API keys locally, but document content is sent to the selected provider API for processing. It cannot override provider privacy, retention, training, or confidentiality policies. Keys should never be committed to the repository.\n\nImportant disclaimer:\n\nChronicle uses AI-assisted extraction workflows, so outputs can still contain errors, omissions, or structural mistakes. It is designed to reduce cleanup and improve reviewability, not replace human verification. It should not be relied on as the sole basis for legal, medical, financial, compliance, or safety-critical decisions.\n\nChronicle is still being actively tested and refined, and thoughtful feedback is very welcome.\n\nFor now, the public feedback path is GitHub Issues:\nhttps://github.com/harry6116/Chronicle/issues",
  "title": "Introducing my app chronicle, a visually intelligent document reader"
}