vex — security grade SAFE, quality 54/100

Security audit verdict: SAFE · quality 54/100

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 AKMessi · Agent Tool · ★ 85

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

🔒 Is vex safe to install? View the security audit →

About vex

Vex Terminal-first AI video editing, driven by plain English. Vex is a source-available, non-commercial AI video editing agent for the terminal. Launch , talk to it in plain English, point it at a video file, and it edits a safe working copy of your footage using FFmpeg, MoviePy, transcript intelligence, generated visuals, and an LLM-driven tool loop. It is built for creators and builders who want CLI speed without memorizing editing commands, FFmpeg flags, subtitle workflows, color-correction knobs, or export presets. Highlights | "Auto color grade this properly

agentic-harnessai-agentvideovideo-editingvideo-editing-agentvideo-editing-toolsvideo-editing-workflow

Quick Facts

Stars85
Forks12
LanguagePython
CategoryAgent Tool
Quality Score53.8165494307233/100
Open Issues5
Last Updated2026-09-23
Created2026-03-09
Platformsclaude-code, python
Est. Tokens~25k

Compatible Skills

These tools work well together with vex for enhanced workflows:

  • oh-my-cassette — semantic(0.68)+complementary+same_lang+similar_pop+shared_platform (74%)
  • FireRed-OpenStoryline — semantic(0.74)+complementary+rare_topics+same_lang+shared_platform (70%)
  • mcp-video — semantic(0.53)+complementary+same_lang+similar_pop+shared_platform (69%)

vex alternative? Top 6 similar tools

Looking for a vex alternative? If you're comparing vex 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.

  • cutcli-cookbook by xuliang2024 · ⭐ 190

    Cookbook, JSON templates, AI prompts and docs for cutcli — the CapCut / Jianying (剪映) draft CLI. Generate edit

  • wonda by degausai · ⭐ 152

    Wonda CLI — AI-powered content creation from your terminal

  • mcp-video by KyaniteLabs · ⭐ 72

    Guardrailed video editing MCP server for AI agents. FFmpeg, Hyperframes, repurposing tools, Python client, and

  • skillport by gotalab · ⭐ 406

    Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.

  • groundhog by ghuntley · ⭐ 405

    Groundhog's primary purpose is to teach people how Cursor and all these other coding agents work under the hoo

  • UnityMCP by isuzu-shiranui · ⭐ 314

    Drive the Unity Editor from an AI agent or the terminal. The Editor serves MCP itself over HTTP, so there is n

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is vex?

vex is claude code for video editing. It is categorized as a Agent Tool with 85 GitHub stars.

What programming language is vex written in?

vex is primarily written in Python. It covers topics such as agentic-harness, ai-agent, video.

How do I install or use vex?

You can find installation instructions and usage details in the vex GitHub repository at github.com/AKMessi/vex. The project has 85 stars and 12 forks, indicating an active community.

What are the best alternatives to vex?

The top alternatives to vex on Agent Skills Hub include cutcli-cookbook, wonda, mcp-video. 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 Agent Tool tools