Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A minimal character terminal (console) REPL UI for controlling ffmpeg via natural language descriptions of input files and the desired outcome, powered by local or remote LLM. Shell-style history with arrow keys support, !subshell support, /slash REPL op commands, run-time, env, and cli configuration.
| Date | Stars |
|---|---|
| 2026-07-31 | 329 |
| 2026-08-06 | 329 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
Update! Sorry to anyone that tried to run the code in main for the last week or so. wtffmpeg suffered a "works on my machine" moment when I pushed a commit where things were broken (or merged one, I did't look that hard, I just fixed it as soon as I noticed, after pulling from a repo to a machine that never had a working install of wtffmpeg before, and finding it not to work.) The shame is mine. It is fixed now. ---- I have a tendency to use _1000 words_ when a picture might suffice. So, to make the point - before or instead of you reading all my sometimes rambling words below. Here is **wtffmpeg** in action! I have moved much of the [excessive rambling to here](https://medium.com/@scott.vr/some-months-back-i-released-a-silly-tool-as-a-poc-console-repl-interface-to-a-local-llm-that-56ed5f7284ec?postPublishedType=repub), should you want some. https://github.com/user-attachments/assets/75222305-efe3-4581-9172-b6d76ad37eba ## WTF is this? `ffmpeg`?  -- `wtffmpeg` is a command-line tool that uses a Large Language Model (LLM) to translate plain-English descriptions of video or audio tasks into **actual, executable `ffmpeg` commands**. It is intended to eliminate a common workflow where you know that ffmpeg is the right tool for a job, so you: 1. Search Stack Overflow 2. Read a 1000-word explanation 3. Copy/paste/typo, possibly misunderstand one or more conflicting amswers 5. Read help/usage because the Internet strangers only got you very close to what you want to do. 6. Repeat. And repeat that workflow each and every time the occasion arises where ffmpeg comes to mind as the right tool for the job. (because it likely is the right tool for the job.) ---- To help with that, `wtffmpeg` is designed to help you get what you want by saying what you want. It is not a "GUI for ffmpeg". It is still a console tool like your shell, and ffmpeg is still executed idempotently - stateless and atomic in its execution, isolated from all previous invocations. ffmpeg is a _pure function_. `wtffmpeg` is the stochastic shell, that also happens to be pretty savant-like in its auto-completion and competent in its interpretataion of *DWIM*. Like the mighty ffmpeg, `wtffmpeg` is still a CLI; the command is the point. Its REPL was intended as an **assisted cli explorer**, not just a **one-shot command guesser with a cheat sheet**. The importance of conversation history in the LLM's context **should not be underestimated**. Being able to do something like ``` wtffmpeg> ok now just like that, but have it create chapters in the video container, using periods when audio drops below some threshold for more than 100 milliseconds" ``` and to have the LLM know what "_just like that_" means, because it knows the previous command you are referring to and what its answer to you was, is quite powerful. As is the ability to navigate your command (and prompt) history as you would in your normal shell cli shouldn't be understated. Importantly, although the LLM has all of its full "thoughts" about its response in its short term context memory, it never clutters your interface, so you never have to read through paragraphs about what ffmpeg is, how it can be used, etc while relating it to something that shows how "thoughtful" you are, in that obsequious LLM-as-sycophant manner we all know. But the context is not lost: you have a shell-like command and prompt history you can scroll through, and the LLM has the whole conversation in context. It turns out to be a very capable implementation for getting this kind of work out of an LLLM, and unlike whatever **hype-of-the-week** agent is flooding your newsfeeds this week is doing, wtffmpeg is not executing any commands on your behalf. They all just appear as if by magic at your command-line for you to execute or not. No back-and-forth dialog, no worries about its autonomy; you maintain control. (And by the
Excerpt of 18,473 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:76b4aabf3ecb414d, topic:llm