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 michaelswissa · Agent Tool · ★ 121
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is jevry safe to install? View the security audit →
A browser built around Jev. Language models plan. Jev decides. Chromium acts.An open-source desktop browser that turns natural-language tasks intostructured decisions, guarded actions, and observable results. Install · Demo · Why Jev? · Architecture · Benchmarks · Contribute Jevry explores a practical question: what happens when a browser's next action is a typed model decision? The browser observes its current state, offers the actions it can actually execute, and asks TypeSafe's Jev to
| Stars | 121 |
| Forks | 3 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 65.0986853182318/100 |
| Last Updated | 2026-10-01 |
| Created | 2026-09-24 |
| Platforms | browser, node |
| Est. Tokens | ~19k |
These tools work well together with jevry for enhanced workflows:
Looking for a jevry alternative? If you're comparing jevry with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A modern desktop application for managing Model Context Protocol (MCP) servers across multiple AI agents
Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes
Visual org-chart desktop app for managing Claude Code agent teams, skills, and configurations
🖥️ A native desktop client for OpenClaw premium UI experience without the browser. Built with Electron + Rea
🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
AI said it finished. Flyto2 shows the proof.
Explore other popular agent tool tools:
jevry is Your browser. Ready to act. An MIT-licensed desktop browser agent for website tasks, cited research, and supported games.. It is categorized as a Agent Tool with 121 GitHub stars.
jevry is primarily written in TypeScript. It covers topics such as ai-agents, browser-automation, desktop-app.
You can find installation instructions and usage details in the jevry GitHub repository at github.com/michaelswissa/jevry. The project has 121 stars and 3 forks, indicating an active community.
jevry is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to jevry on Agent Skills Hub include mcp-gearbox, palot, Claude-Agent-Team-Manager. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: