User repository on GitHub
JEVsnap: private screenshot redactor for macOS, Linux, and Windows, powered by Jev
- Forks
- 1
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Tools & CLIs
JEVsnap
A screenshot hotkey redactor for macOS, Linux and Windows that blacks out API keys, tokens, emails, phone numbers, names, internal hostnames and QR codes before the image reaches the clipboard; optional AI checks use the TypeSafe Jev API.
- Stars
- 3
- Language
- TypeScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- brainstormity
- Last verified
- Oct 2026
Used inJev for Security & Privacy
- Languages
- TypeScriptSwift
- Platforms
- macOS
- Capabilities
- Open sourceRuns locallyRequires API key
Highlights
- Screenshot hotkey that blacks out secrets and personal information before the image reaches your clipboard.
- Detects API keys, tokens, emails, phone numbers, names, internal hostnames and QR codes.
- Local rules and on-device OCR run first; optional AI checks call the TypeSafe Jev API.
- macOS 13 and up is Swift with Apple Vision OCR; Linux and Windows use Electron plus TypeScript with bundled offline Tesseract.
- Shared detector test vectors keep the Swift and TypeScript detectors identical; MIT, v0.2, created and pushed 2026-10-15.
Watch out
README and GitHub metadata reviewed 2026-10-17; the excerpt stops inside the detection pipeline, so detector coverage, false-positive rates, key setup and Windows verification are not evidenced. The author warns no automatic redactor is perfect.
Questions about this entry
Short answers drawn from the linked project or page.
A screenshot tool with a hotkey that automatically blacks out secrets and personal information before the image reaches your clipboard, so pasting a capture into a chat is less likely to leak credentials or private data.
Per the README: API keys, tokens, emails, phone numbers, names, internal hostnames and QR codes, with the list continuing past what the digest excerpt shows. Both the macOS and Electron builds share the same detector cases.
After local rules and on-device OCR, optional AI checks use the TypeSafe Jev API. Those checks are a second layer rather than the primary mechanism, and the project describes itself as an unofficial community project not affiliated with TypeSafe.
macOS 13 and up via a Swift and AppKit app with Apple Vision OCR, built and tested on macOS with test suites configured in CI. Linux and Windows use an Electron plus TypeScript app with bundled offline Tesseract, tested on Linux, with Windows exercised only by CI.
The OCR step is on-device in both builds, local rules run first, and Tesseract is bundled and offline on Linux and Windows. Only the optional AI checks send anything to the TypeSafe Jev API.
Yes, possibly. The README warns that no automatic redactor is perfect and that JEVsnap lowers the chance of leaking something but does not replace a quick look before you post.
Version v0.2, MIT-licensed, created and pushed on 2026-10-15, with 3 stars and one fork in the digest metadata. It is an unofficial community project not affiliated with TypeSafe.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: Kubernetes admission control with a decision model, fail-closed.
Hacker News: SafeDep Gryph plus Jev checks for compromised coding-agent behavior.
2 pointsDetecting Compromised AI Coding Agents with Jev and GryphRead the thread on Hacker NewsX: Jev and Laya on security queries
X: Testing Jev for prompt injection
More Jev resources like this
A local, non-autoregressive security guardrail suite powered by Convai Innovations' Laya model, returning typed decision probabilities for security inspection. It positions itself against Jev on latency and against generative LLMs on hallucination risk.
Jev Tools & CLIs#community#github#security
Python CLI and agent skill that reviews Agent Skills, MCP configs, and source code for suspicious behavior with TypeSafe Jev plus local static checks, reporting file and line evidence, risk categories, model probabilities, and unscanned scope.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
win4r/jev-security-scanPython
win4r/jev-security-scanPythonCisco's security scanner for agent skills added a System One analyzer: it sends the full skill text to POST /v1/systemone as one advisory Noul question and records the probability, while being deliberately unable to emit a finding or change a severity.
Jev Tools & CLIs#community#security#agent-skills
Community
cisco-ai-defense/skill-scannerPython
cisco-ai-defense/skill-scannerPythonA guard that stands outside an LLM agent and uses TypeSafe Jev to score both incoming prompts and proposed actions, turning the score into a block, a question, or a pass; in the README's Gandalf test it rejected 17 of 21 published injection prompts before send.
Jev Tools & CLIs#community#github#security
Community
JamesANZ/JevPromptShieldTypeScript
JamesANZ/JevPromptShieldTypeScriptFloating real-time translated subtitles for Japanese and English video and livestreams on Android, macOS, and Windows: speech recognition runs fully offline with bundled models, translation uses your own OpenAI-compatible endpoint, and optional TypeSafe Jev helpers refine the result.
Jev Tools & CLIs#community#github#subtitles
Community
korenkrita/simul-subtitleKotlin
korenkrita/simul-subtitleKotlinA local stdio MCP server from bgivenb that runs whole browser and macOS goals for your agent: your agent supplies the goal, exact values, and completion conditions, and Flick loops observe, decide, and act with TypeSafe Jev. TypeScript core with Playwright and Swift drivers.
Jev Agents & MCP#community#github#mcp
Community
bgivenb/flick-computer-useTypeScript
bgivenb/flick-computer-useTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.