Framesail is the AI video platform for long-form YouTube: one pipeline that takes a script to a finished video, with your characters and style locked across every shot.

Making long-form AI video today means 8+ tabs stitched by hand — an LLM for the script, a voice model, an image model, a video model — copying assets and prompts between them, with characters drifting between tools and style resetting at every export. Templated tools have the opposite problem: preset styles, generic stock characters, short clips instead of episodes. Framesail replaces both: one pipeline, end to end, in your style.

The pipeline has six stages. Style: paste images, videos, or YouTube links and Framesail reverse-engineers the look, voice, and direction, then reuses it across every video. Script: describe your idea and let AI write in your narrative style, or write it yourself. Reference images: Framesail reads your script and generates a reference image for every character, place, and prop, so visuals stay consistent scene to scene. Voiceover: one narrator or multiple characters, each with their own voice, timed word by word. Storyboard: planned scene by scene using your style, characters, and voiceover. Editor: add captions, music, and sound effects — or just tell the director what to change — then export.

Framesail is also fully agent-controllable: a REST API plus an MCP server with 65+ tools, so an agent like Claude Code can run the whole pipeline while you make the key decisions. And a BYOK plan runs covered jobs on your own provider keys — zero credits, no token markup.

No black box: you control every prompt, asset, model, and setting at every step.

CodeHerald provides a new way to keep track of your code review queue, grouped by your next action needed.

When would you use CodeHerald?

• You work in a team that does code reviews.
• Your team receives ad-hoc code review requests via multiple channels: DMs, emails, bookmarks of filtered lists.
• Your team sometimes loses track of small pull requests, delaying them days.
• Your team find ad-hoc code review requests distracting, but cannot put a finger on why.
• Your team tried different strategies to improve code review process, and none of them felt right.

If any of the above is true, CodeHerald will help you.

What can CodeHerald do for you?

CodeHerald groups pull requests by next action: must review, needs an update, can be merged. It allows you to replace slack, emails, filters, and browser bookmarks with one single page that you can open at a glance and decide which PR to tackle next.