Maskify
Mask personal data in TXT, PDFs and DOCX, in your browser
Maskify launched on May 10, 2026 with 1 votes.
What it does
Most document redactors either upload your file to a third-party API or paint rectangles over text that's still selectable underneath. Maskify keeps the original PDF/DOCX in your browser; only the extracted text is sent for detection. PDF export is rasterised, so the original bytes are physically removed — DOCX is edited in-place, preserving styles and images. Hybrid detection: in-house AI plus validated regex (IBAN, card, DNI) and your own saved patterns. Reversal map only you hold.
Maskify enmascara información personal (nombres, DNI, IBAN, emails, teléfonos, tarjetas) en PDF, DOCX, TXT y Markdown. Detección con IA propia, sin terceros, con mapa de reversión que solo guardas tú.
Sube un documento, elige qué tipo de información ocultar, y descarga una versión segura. Sin servidores externos, sin telemetría. Modelo de IA propio + reglas con validación matemática (IBAN, DNI, tarjetas, claves API…). Sin pasar por terceros. Activa o desactiva cada categoría de dato. Revisa cada coincidencia antes de exportar. El mapa de reversión se genera en tu navegador y se descarga solo a tu disco. Nunca toca nuestros servidores. Activa los que necesites. Cada tipo puede estilizarse como etiqueta, bloque, asterisco ofrom maskify.es
Does a similar job
all alternatives →
- FDFree document masker – replace PII in unstructured text2019 · translate.tonic.ai · ▲11




More ai this month
the category →



Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video

Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai



Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com

🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com