This looks awesome, the browser‑only approach is a boon for my potato PC. Excited to try it out.

Really impressive execution on the agentic workflow architecture. The challenge you mentioned about "asking more questions upfront" instead of rigid workflows resonates deeply from building production AI agents. The key insight is that agentic systems work best when they have rich context about user intent rather than trying to guess from minimal input. Video editing is particularly challenging because the feedback loops are expensive (unlike text where you can regenerate cheaply), so getting the planning phase right is critical. Your approach of treating it like distributed systems with proper error handling and recovery makes complete sense. Looking forward to seeing how you handle the "verification problem" - knowing when the agent made the right creative decisions without human review.

Can it help make creating seamless loops easier?

this looks like a "freecut.net" fohk (fork)

Beautiful site!

Congrats on the launch. The client-side rendering on WebCodecs/WebGL2 is impressive — that alone is a hard technical problem most teams avoid.

One thing I've been thinking about building in this space: there's a fundamental split between understanding what to edit (where VLMs/agents shine) and executing the edit precisely (where you need deterministic operations, not model inference).

Most "AI video editors" blur these two together — they use the same probabilistic approach for both understanding and execution. But when a user says "cut the first 3 seconds and add a 0.5s crossfade," that shouldn't go through a model. That should be a precise, repeatable operation.

The Cursor analogy in your roadmap is apt — Cursor works because it predicts intent but executes through deterministic code transforms, not by asking an LLM to write the whole file. Same principle applies to video.

Curious how you handle the boundary between agent-proposed edits and deterministic timeline operations under the hood?

- lots of players in the market doing this

- https://news.ycombinator.com/item?id=42806616

- https://news.ycombinator.com/item?id=45980760

- https://news.ycombinator.com/item?id=46759180

- https://github.com/saurav-shakya/Video-AI-Agent

- going to be rather tough to differentiate

This is a crazy question, but I would like to know how close I can get to the following:

I would like to:

- upload a bunch of surf footage

- let it sort through the surfers

- pick the three longest waves surfed by each surfer

- create a montage grouped by surfer, ordered by shortest to longest wave for that surfer.

Thank you!