Sabitlenmiş Tweet
Editframe
26 posts
Editframe
@editframe
Build video with code
New York, NY Katılım Ekim 2017
2 Takip Edilen1.2K Takipçiler
Editframe retweetledi
I completely vibecoded the following presentation using codex + @editframe + @ElevenLabs for the voice over using my cloned voice. This video is about my personal AI stack using @runneragent + my personal site dcbuilder.dev + codex + @obsdmd and many other tools. Enjoy!
English
Editframe retweetledi
We’re building the temporal creative layer for agents, and humans in the loop.
Bring your favorite tools @ElevenLabs , @splice , use your favorite ide, use any model. it’s not just making a video with a prompt, it’s building systems of creation for agents.
agents need video
dcbuilder.eth ⚪️@dcbuilder
Creating videos with AI has never been easier, making an internal product demo of Centaur from Paradigm/Tempo and I'm using Codex + EditFrame for generating the animated video and script, ElevenLabs for the VoiceOver and Splice + Epidemic Sound for the music
English
Editframe retweetledi
Creating videos with AI has never been easier, making an internal product demo of Centaur from Paradigm/Tempo and I'm using Codex + EditFrame for generating the animated video and script, ElevenLabs for the VoiceOver and Splice + Epidemic Sound for the music
English
Editframe retweetledi
This video took only 2 prompts and around 10 minutes to produce.
The workflow was ridiculously simple.
I used Codex to build the flow.
I used @editframe to generate the video.
LLMs are starting to feel like they’re actually sitting in the editor’s chair now.
Oktay Dak@dakmaybe
Hanımlar, beyler. Bugün @oesnadaki uzun süredir eksikliğini hissettiğimiz bir katmanı açıyoruz. Karşınızda .oesnada Relay. oesnada.com/relay
English
The more i use `/goal` the more I want to ensure the model gets simple facts right up front. So I use a version of @mattpocockuk grill-me focused on @Everlier's methodology around facts.
Facts allow me to describe very clear requirements for a feature or system. & Not always that technical. The more I do with AI, the less patient I get, so I can't read a ton of markdown, but I can afford to read/verify simple lists of facts.
Once facts are established i let the agent refine a plan for itself (every decision aligned to those facts) so it can figure out order of operations.
have been having a lot of fun with this process.
composition by @editframe
English
Editframe retweetledi
Me hablo @yudDIDit de @editframe y probe hacer una POC de usar su herramienta para automatizar los videos de @pavla_app con Buffer y @cursor_ai y la diferencia de velocidad de renderizacion en comparacion con Hyperframes es absurda.
Pase de 3 minutos a 12 segundos renderizando.
Español
Editframe retweetledi
Jeremy and team are incredible, so stoked for their release
Jeremy Yudkin@yudDIDit
Today, @editframe emerges from stealth. Agents need video. Editframe Agent Skills: npm create @editframe@latest Just prompt Claude Code, Cursor, or Codex and get a working video or a full interactive GUI. This video was created just by prompting 👇
English
Editframe retweetledi
For folks interested in the code used for generating this video using @editframe , here's the repo:
Misbah Syed@MisbahSy
I asked claude why Editframe? Claude made this using Editframe, the result… 🤯 watch till the end 🔊
English
Editframe retweetledi
@sun_anshuman @yudDIDit @editframe @Remotion We're built one layer down the stack using custom html elements + css.
So you can get a lot done with purely declarative syntax.
Of course, you can (should) layer on scripting, and we do ship official React components for our html tags.
English
Editframe retweetledi
Editframe is how agents are going to create and edit video for you. Agents will allow ten times as many people to create, and video is the largest creative market…
Jeremy Yudkin@yudDIDit
Today, @editframe emerges from stealth. Agents need video. Editframe Agent Skills: npm create @editframe@latest Just prompt Claude Code, Cursor, or Codex and get a working video or a full interactive GUI. This video was created just by prompting 👇
English
Editframe retweetledi
Super excited for Jeremy and Editframe today
Can't stop thinking about this since he and I last chatted: A new round of format wars are upon us. As agents grow increasingly capable, open formats have a powerful tailwind due to their legibility.
Editframe is an intersection of these things: an open format for video editing built on HTML/CSS, so it's familiar enough to untrained agentic tools to use on the fly. Using it the past few months, it one-shots things I wouldn't have the slightest clue how to do in Final Cut or Premiere. Agents can't use those tools effectively either because their formats are illegible.
LLM legibility can be bootstrapped by deriving from existing formats in other domains.
Not an investor, just a fan and friend!
Jeremy Yudkin@yudDIDit
Today, @editframe emerges from stealth. Agents need video. Editframe Agent Skills: npm create @editframe@latest Just prompt Claude Code, Cursor, or Codex and get a working video or a full interactive GUI. This video was created just by prompting 👇
English
Editframe retweetledi
jeremy is a machine, if anyone can figure out this space its him and his crew.
I know my agents are hungry for more tools, this is gonna be interesting.
Jeremy Yudkin@yudDIDit
Today, @editframe emerges from stealth. Agents need video. Editframe Agent Skills: npm create @editframe@latest Just prompt Claude Code, Cursor, or Codex and get a working video or a full interactive GUI. This video was created just by prompting 👇
English
Editframe retweetledi
Okay, this is pretty dope.
Jeremy Yudkin@yudDIDit
Today, @editframe emerges from stealth. Agents need video. Editframe Agent Skills: npm create @editframe@latest Just prompt Claude Code, Cursor, or Codex and get a working video or a full interactive GUI. This video was created just by prompting 👇
English
Editframe retweetledi
Editframe retweetledi
When you're building with video, being 99% right is 100% wrong.
Letting the agent cook, using what it knows already, is correct. LLM's and models were trained on HTML/CSS, and leveraging everything the browser had. We help you package that into an MP4.
But there is more work to video than just the syntax, and to really get it right for agents and video.
Just like there is much more to a database, storage, etc.
What’s missing for real production? Agents are great, the models are great, but the gap is running video workflows in production (for agents and humans).
Large videos need proper streaming playback, cloud rendering when the browser isn’t enough, and easy human-in-the-loop workflows.
The enterprise needs secure ways for their agents to operate, that work.
Anyone who's built in video (with any scale and with any quality) knows how hard this problem actually is.
That’s why we built the full stack with @editframe
• Custom HTML element with built in streaming playback
• Cloud rendering API (parallel rendering 1000s of videos)
• Declarative GUI toolkit (, , etc.) so agents + humans can actually collaborate with forms and editors
Editframe provides a format that LLM's have been fully trained on, works natively in the browser, works reliably at scale and in production.
This is what going from prototype to production in video really looks like. This is what does not exist.
A full agent video platform that actually lets you build.
Jeremy Yudkin@yudDIDit
Today, @editframe emerges from stealth. Agents need video. Editframe Agent Skills: npm create @editframe@latest Just prompt Claude Code, Cursor, or Codex and get a working video or a full interactive GUI. This video was created just by prompting 👇
English
Today, @editframe emerges from stealth. Agents need video.
Editframe Agent Skills:
npm create @editframe@latest
Just prompt Claude Code, Cursor, or Codex and get a working video or a full interactive GUI.
This video was created just by prompting 👇
English
@PeteCapeCod @yudDIDit Awesome Peter! Hope to see what you come up with :D
English
@yudDIDit @editframe Dude this is sick!!!!! 🤩 Total game changer 🍻
Well there goes my evening lol
English
@sososazesh @yudDIDit Thanks Soso, we're excited to see what people make!
English
Editframe allows agents to edit video 🤯
Congrats on the launch @yudDIDit!
Jeremy Yudkin@yudDIDit
Today, @editframe emerges from stealth. Agents need video. Editframe Agent Skills: npm create @editframe@latest Just prompt Claude Code, Cursor, or Codex and get a working video or a full interactive GUI. This video was created just by prompting 👇
English
@DeFidabller @yudDIDit You can render via CLI, or scale up to render in parallel via our cloud service.
English
@yudDIDit @editframe So it’s Hyperframes but you have to pay for it?
I don’t understand
English