free_tools
Small tools,
shipped free.
Chrome extensions I designed and built end to end. Private by default, no account, no tracking, no cost. Install one below, or read how it was built.
Prompt Vault
Free AI prompt manager (Chrome extension)
A free Chrome extension that saves, organizes, and one-click inserts AI prompts into ChatGPT, Claude, Gemini and more. I designed and shipped the whole thing — serverless, private, and reliable across nine different AI chat sites.
- 9
- supported AI chat sites
- Free
- no account · no server
- 100% local
- prompts never leave your browser
- Built a Manifest V3 extension (Vanilla JS + Vite) with a popup for quick insert and a side panel for a nested-folder prompt library with drag-reorder, favorites, tags, and instant search.
- Made insertion resilient across nine AI sites by injecting via chrome.scripting with layered strategies (execCommand, paste event, native setter) and an always-on clipboard fallback, so a site changing its DOM degrades gracefully instead of breaking.
- Added a templating layer: prompts with {{variables}} ask the user to fill the blanks on insert, turning one prompt into many.
TextQuill
Free on-device image-to-text OCR (Chrome extension)
A free Chrome extension that pulls editable text out of any image, screenshot, or region of the screen — and does the OCR entirely on-device, so the image never leaves the browser. I designed and shipped the whole thing: nine ways to capture, sixteen languages, and a private, account-free workflow. Lives at textquill.app.
- 16
- OCR languages
- 9
- ways to capture
- 100% on-device
- images never leave your browser
- Built a Manifest V3 extension that runs OCR on-device via a WebAssembly engine — no cloud upload, no account, no network round-trip for the image, so it works offline and keeps sensitive images private.
- Shipped nine capture paths so text can be grabbed wherever it lives: right-click an image, region select (Alt+Shift+S), visible or full-page capture, file upload, drag-and-drop, clipboard paste, an image URL, or a base64 data URL.
- Supported sixteen languages (English, Hindi, Nepali, Japanese, Chinese, Korean, Arabic, and more) with Fast, Accurate, and Auto modes so the user can trade speed against precision per job.
and_the_bigger_work
These are the small end. The rest is full products.
Frontend, backend, cloud, and the AI on top, shipped to a bar you can defend in production.
See ways to work together
