jev-voice-browser — security grade SAFE, quality 60/100

Security audit verdict: SAFE · quality 60/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by moritzkremb · AI Tool · ★ 141

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is jev-voice-browser safe to install? View the security audit →

About jev-voice-browser

voice-browser — talk to a real browser, it acts before you finish the sentence A Node app that controls a headed Chromium window (Playwright) by voice. Speech is streamed word by word from the browser's Web Speech API to a small Node server; on every partial transcript the server asks Jev (TypeSafe's System One model, ) one request with a dozen typed questions — intent, target element, site, "is the command complete?", "is this even addressed to me?", "is it destructive?" — gets typed probabilities back in 250–350 ms, and code decides whether to act, wait, ask, or ignore. Jev never generates text. Search queries, typed text and URLs are extracted as candidate spans by code and Jev only picks one, which is copied verbatim. Run it Requi

Quick Facts

Stars141
Forks18
LanguageJavaScript
CategoryAI Tool
LicenseMIT
Quality Score60.1952968786758/100
Open Issues2
Last Updated2026-09-17
Created2026-09-17
Platformsbrowser, node
Est. Tokens~7k

Compatible Skills

These tools work well together with jev-voice-browser for enhanced workflows:

  • realbrowser — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • awesome-jev-projects — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)

jev-voice-browser alternative? Top 5 similar tools

Looking for a jev-voice-browser alternative? If you're comparing jev-voice-browser with other ai tool tools, these 5 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • MedgeClaw by xjtulyc · ⭐ 668

    Open-source AI research assistant for biomedicine — chat to run RNA-seq, drug discovery, clinical analysis, an

  • SciToolAgent by HICAI-ZJU · ⭐ 416

    SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration

  • redesigned-pancake by Sfedfcv · ⭐ 256

    Skip to content github / docs Code Issues 80 Pull requests 35 Discussions Actions Projects 2 Security Insights

  • claude-code-voice-skill by abracadabra50 · ⭐ 169

    Skill to talk to Claude about your projects over the phone

  • maui-skills by davidortinau · ⭐ 163

    .NET MAUI skills for GitHub Copilot and Claude Code

More AI Tool Tools

Explore other popular ai tool tools:

View all AI Tool tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is jev-voice-browser?

jev-voice-browser is Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.. It is categorized as a AI Tool with 141 GitHub stars.

What programming language is jev-voice-browser written in?

jev-voice-browser is primarily written in JavaScript.

How do I install or use jev-voice-browser?

You can find installation instructions and usage details in the jev-voice-browser GitHub repository at github.com/moritzkremb/jev-voice-browser. The project has 141 stars and 18 forks, indicating an active community.

What license does jev-voice-browser use?

jev-voice-browser is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to jev-voice-browser?

The top alternatives to jev-voice-browser on Agent Skills Hub include MedgeClaw, SciToolAgent, redesigned-pancake. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse AI Tool tools