ONYRI Sanitize
Get the most out of AI without handing them your data.
ONYRI Sanitize launched on June 6, 2026 with 20 votes, #853 of 22,647 launches that month and more than 95% of that year's launches.
What it does
Most AI-privacy tools redact on their servers — your data still leaves your machine. ONYRI Sanitize doesn't: detection, masking and restoration run 100% in your browser, and the token↔value mapping never touches a server. 0 bytes of sensitive data ever leave. What stands out: • Reversible tokens, not black boxes — the AI keeps context; you restore values in place • 38 detectors, 6 families: names to API keys, salaries to cloud secrets • Text, CSV/Excel + built-in Chat for GPT, Claude & Mistram
Hide your private info — names, emails, card numbers — before you write to an AI like ChatGPT. The answer comes back, and everything stays on your computer.
ONYRI Sanitize finds the private bits in your text — names, emails, card numbers — and hides them before you send anything to an AI. The real answer comes back to you, complete. Everything happens on your computer. Nothing is sent. 38 types across 6 families. Three areas to protect — framed by what you no longer want leaving your machine. Names, emails, phone numbers, IBANs, social security numbers, addresses, ID documents, medical information. AWS · GCP API keys · OpenAI, Stripe, Anthropic keys · Slack tokens · inline passwords · SSH keys. Internal project names, infrastructure URLs, meeting markers, salaries, company IDs, client and partner names. Pasting a customer export, a support…from onyri-sanitize.com
Does a similar job
all alternatives →
Anakin2021 · anakin.io · ▲148Every second thing I build needs to access the web, and I was frustrated with not finding something that just works all the time. With my team, we built this because I wanted to enable access to extremely difficult websites and apps for every AI agent. We have solved this cat-and-mouse problem with self-healing built in. It's one API to get data from hostile sites, and it can do easy sites too. You POST a URL and get back Markdown, JSON, HTML, a screenshot, or all of them. That same call handles anti-bot, proxy rotation, JS rendering, persistent authenticated sessions, and schema-based…
AI Safeguard2025 · aisafeguard.co.uk · ▲14Prevent sensitive data leaks in popular LLM's like ChatGPT
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 · 28d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, June 2026
the whole month →
Fundraisly▲1,537AI fundraising agent that finds investors and books meetings
AI · Jun 2026 · fundraisly.com
Homebrew 6.0.0▲1,481Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!
Dev tools · Jun 2026 · brew.sh
Hi HN! I was super frustrated at apps like tiktok and wechat preventing me from saving or downloading the animated gifs, so I made a little tool to turn a screen recording into a slack-sized emoji. Hope you get some value from this!
Life & fun · Jun 2026 · vorpus.github.io
Search 18 years of Hacker News and chart how any topic, tool, or person trended. Overlay terms to compare their rise and fall across 45M posts and comments.
Life & fun · Jun 2026 · hackernewstrends.com