llmpeg — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 gstrenge · Agent Tool · ★ 147

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

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

About llmpeg

llmpeg (Windows works fine, just a windows specific test is failing for poor reason, working on updating the test!) Let's be honest, who really knows how to use . Its that tool that is so helpful but not needed enough to justify learning all of its inner workings. The days of scrolling through stackoverflow are over, with . This CLI tool interfaces with an OpenAI LLM (and has support for other LLM API providers) to convert your plain text commands into OS/platform specific ffmpeg commands. is a powerful wrapper around the popular multimedia library , designed to simplify video and audio processing for users who are not familiar with the intricacies of commands. By leveraging language model technology, allows users to describe their multimedia processing tasks in natural language, and the tool generates and executes the appropriate [](https://github.com/FFmpeg/

ffmpegllmopenaivideo

Quick Facts

Stars147
Forks10
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score70.2295798862827/100
Open Issues2
Last Updated2024-04-26
Created2024-04-23
Platformscli, python
Est. Tokens~867k

llmpeg alternative? Top 6 similar tools

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

  • wcgw by rusiaaman · ⭐ 674

    Shell and coding agent on mcp clients

  • UnrealGenAISupport by prajwalshettydev · ⭐ 650

    Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gem

  • openclip by linzzzzzz · ⭐ 549

    OpenClip - AI-powered highlight extraction for long videos (AI 驱动的长视频精彩时刻提取工具)

  • mcp-linker by milisp · ⭐ 340

    MCP store. Discover, add & syncs configuration manager across clients like Claude code, Codex, Cursor💡mcphub

  • oreilly-ai-agents by sinanuozdemir · ⭐ 299

    An introduction to the world of AI Agents

  • vibeframe by vericontext · ⭐ 173

    Frontier AI video generation for coding agents - Seedance, Runway, Veo, Kling on your own keys, behind a hard

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is llmpeg?

llmpeg is Let's be honest, who really knows how to use ffmpeg. Its that tool that is so helpful but not needed enough to justify learning all of its inner workings. The days of scrolling through stackoverflow a. It is categorized as a Agent Tool with 147 GitHub stars.

What programming language is llmpeg written in?

llmpeg is primarily written in Python. It covers topics such as ffmpeg, llm, openai.

How do I install or use llmpeg?

You can find installation instructions and usage details in the llmpeg GitHub repository at github.com/gstrenge/llmpeg. The project has 147 stars and 10 forks, indicating an active community.

What license does llmpeg use?

llmpeg is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to llmpeg?

The top alternatives to llmpeg on Agent Skills Hub include wcgw, UnrealGenAISupport, openclip. 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