GitHub · Builds and renders the video

Make a product launch video with GitHub Copilot CLI

GitHub Copilot CLI brings the Copilot coding agent to your terminal: it reads your repository, edits files and runs commands with your approval.

With Kuchi connected it can find a launch video that fits your product, plan your version shot by shot and build it in the repo.

By Founder & Research Lead, Kalaris Labs · Updated

Step by step: GitHub Copilot CLI and Remotion: render a product video

Connect Kuchi to GitHub Copilot CLI

No sign-in, no API key. The server is https://kuchi.kalarislabs.com/mcp.

  1. Add the server from your terminal. It is saved to ~/.copilot/mcp-config.json. No sign-in is needed.

    copilot mcp add --transport http kuchi https://kuchi.kalarislabs.com/mcp
  2. Or, inside a Copilot CLI session, type /mcp add and enter the same URL.

  3. Paste the setup prompt from this page.

Why use GitHub Copilot CLI for your launch video

  • Lives next to your repository and its pull requests.
  • Asks before running commands, so the build stays under your control.
  • Uses the Copilot plan you already have.

How it works

  1. 1

    Choose a template

    A short list of real launch videos ranked for your product, with posters and links.

    kuchi_suggest_templates
  2. 2

    Study it

    Every shot's exact frames, how it enters, how much moves, its colours and a sheet of real frames.

    kuchi_get_breakdown
  3. 3

    Plan the remake

    Your product details mapped onto the reference's frames, with a list of anything still missing.

    kuchi_plan_remake
  4. 4

    Build

    GitHub Copilot CLI writes the scenes shot by shot, using Kuchi components where they fit, and renders the video.

    kuchi_get_component
  5. 5

    Check

    Compare your frames with the reference at the times it returns, and fix what differs.

    kuchi_check_remake

Prompts to try in GitHub Copilot CLI

  • Use Kuchi to suggest launch templates for this repository. Show me the posters.

  • Plan the remake of the one I pick and list the assets you need.

  • Build it, render it and run kuchi_check_remake.

How GitHub Copilot CLI loads the MCP server

copilot mcp add --transport http kuchi <url> saves the server to ~/.copilot/mcp-config.json. Inside a session, /mcp add does the same interactively.

Copilot CLI asks before running commands and editing files. Tool calls to this server are read-only on the server side.

The server speaks Streamable HTTP with no authentication. This config is separate from VS Code's.

A full run in GitHub Copilot CLI, step by step

Copilot CLI calls kuchi_suggest_templates, shows posters and waits. It reads the breakdown, classifies the shots and plans.

It scaffolds Remotion, builds the shots on the planned frames and renders. Allow the render command for the folder so the build-check-fix loop does not stop for approval each time.

Run kuchi_check_remake and compare stills before the final render.

What GitHub Copilot CLI sends to the server

The server is a remote MCP server over Streamable HTTP at https://kuchi.kalarislabs.com/mcp. Every message is a JSON-RPC 2.0 request sent as an HTTP POST to that one endpoint. It is stateless: there is no session to keep alive, no cookie and no Authorization header, so GitHub Copilot CLI can reconnect at any time without losing anything.

When GitHub Copilot CLI connects it sends initialize and receives the server's name, version, instructions and capabilities (tools, resources and argument completion), then calls tools/list. The tool list carries a one-hour cache hint, because it only changes when the server is deployed. Each tool call is a tools/call whose arguments are checked against a strict schema: unknown fields are rejected and every string has a length limit, so a malformed call fails with a clear message instead of a half-right answer.

Results come back as text, Markdown by default or JSON when the call passes response_format: "json", and JSON results also arrive as structuredContent. Media is never inlined: the reference MP4, the poster and the storyboard sheets come as resource_link entries pointing at the CDN, which GitHub Copilot CLI can open or fetch itself. A result is capped at 25,000 characters; a long blueprint arrives in pages of up to 40 shots, with shot_offset and shot_limit to fetch the next page.

Every tool is annotated readOnlyHint: true, destructiveHint: false, idempotentHint: true and openWorldHint: false: nothing changes on the server, the same call returns the same answer, and no tool reaches out to the wider web. The server also offers resources (kuchi://workflow, kuchi://videos/{id}, kuchi://breakdowns/{id} and kuchi://components/{name}) with autocompletion, for clients that let you attach a resource to a message.

The 13 tools, and when GitHub Copilot CLI calls them

ToolWhat it returnsWhen GitHub Copilot CLI uses it
kuchi_get_workflowThe remake method, whole or one step (find, study, plan, build, check) with the rules that hold for all steps. Markdown.Read once before the first remake, or one step at a time to keep context small.
kuchi_suggest_templatesA short numbered list of launch videos ranked for a product description, each with poster, link, what fits, what differs, what you would need to supply and one recommendation.First call of a job; the agent shows the posters and waits for your pick.
kuchi_search_videosSearches the whole library by keyword, style, category, format, aspect ratio, length, pace or theme, a page at a time.When you ask for something specific ("vertical, fast, terminal style").
kuchi_get_videoOne video by id, slug, site link or original X link: file, poster, storyboard, length and measured rhythm, with resource links to the MP4 and images.When you paste a link from the site instead of choosing by number.
kuchi_list_filtersEvery valid style, category, format, aspect ratio, pace and theme with counts, plus the 14 shot kinds an agent classifies shots into.Before a filtered search, so it never guesses a filter value.
kuchi_get_breakdownThe frame-by-frame measurement of one video: each shot's start and end, entrance, amount of motion and colour roles, a per-second motion and loudness curve, and storyboard sheets of real frames.Study step; the agent looks at the storyboard and writes its own shot analysis.
kuchi_plan_remakeTakes your product details, assets and the agent's shot analysis; returns a blueprint re-timed to your length on whole frames, with your content per shot, plus missing_inputs and ready.Called until ready=true; the blueprint becomes the shot list in code.
kuchi_check_remakeChecks a shot list against the reference: reused brand text, assets taken from the reference, generated logos or UI, placeholders, timing gaps and drift. Returns passed and compare_frames.Before delivery; the agent renders stills at the compare_frames times and fixes drift.
kuchi_list_componentsLists the copy-paste Remotion components (kinetic type, captions, UI screens, cursors, logos, transitions) with dependencies and shadcn install commands.While building, to find a ready-made component for a shot.
kuchi_get_componentOne component's full source, files, dependencies, install command and usage notes, split into parts when long.To read a component's source before installing or adapting it.
kuchi_send_feedbackReports a failure or a missing capability to the maintainers. The only tool that records what the agent writes.When a tool fails or misleads.
searchThe generic search tool some clients expect: returns up to 10 video ids, titles and URLs.Rarely; the kuchi_ tools are richer.
fetchThe generic fetch tool: one video by the id from search, with notes, links and metadata.Rarely.

How the blueprint times your video

A reference video is measured shot by shot: where each shot starts and ends, how it enters and how much of the frame moves. kuchi_plan_remake maps those shots onto your target length, between 5 and 180 seconds, at the frame rate you will render (12 to 120 fps, the reference's own by default).

If your length is at least 75% of the reference's, every shot is kept and re-timed by the same factor (mode retimed). If it is much shorter, speeding everything up would wreck the rhythm, so the plan keeps an evenly spaced subset of shots, at least three, and re-times those instead (mode condensed). Either way every shot starts on a whole frame and lasts at least one, so start_frame and end_frame are exact integers GitHub Copilot CLI can place directly; no rounding happens later.

Each shot also carries compare_at_s: the moment in your video that matches the reference frame shown on the storyboard, so the side-by-side check compares like with like. precision says whether every shot was classified (analysed), some were (partly_analysed) or none were (timing_only); shots without a kind keep their timing and get placeholder content until GitHub Copilot CLI classifies them. One shot from a blueprint:

{
  "shot": 3,
  "start_s": 4.2,
  "end_s": 6.533,
  "start_frame": 126,
  "end_frame": 195,
  "reference_shot": 3,
  "reference_start_s": 3.9,
  "reference_end_s": 6.07,
  "compare_at_s": 5.1,
  "enters": "transition",
  "motion": "medium",
  "kind": "ui_screen",
  "reference_shows": "Product UI. Dashboard centered, cursor moves to a button",
  "your_content": "Acme: \"Live sync\". A screenshot or recording of the user's product..."
}

In Remotion the blueprint maps one to one onto a composition and a <Sequence> per shot. Saving the plan as plan.json and reading the frames from it means GitHub Copilot CLI never retypes a number:

// src/Root.tsx: one composition at the blueprint's fps and length
import { Composition } from 'remotion';
import plan from '../plan.json';
import { Launch } from './Launch';

export const Root = () => (
  <Composition id="Launch" component={Launch}
    fps={plan.blueprint.fps} durationInFrames={plan.blueprint.frames}
    width={1920} height={1080} />
);

// src/Launch.tsx: one <Sequence> per blueprint shot, on its exact frames
import { AbsoluteFill, Sequence } from 'remotion';
import plan from '../plan.json';
import { shots } from './shots';

export const Launch = () => (
  <AbsoluteFill>
    {plan.blueprint.shots.map((s) => {
      const Shot = shots[s.shot];
      return (
        <Sequence key={s.shot} from={s.start_frame}
          durationInFrames={s.end_frame - s.start_frame + 1}>
          <Shot />
        </Sequence>
      );
    })}
  </AbsoluteFill>
);

Use 1080×1920 for 9:16 and 1080×1080 for 1:1. Inside a <Sequence>, useCurrentFrame() starts at 0, so each shot's entrance animation is written relative to the shot, not to the whole video.

The 14 shot kinds GitHub Copilot CLI classifies

While studying the storyboard, GitHub Copilot CLI gives every reference shot one kind. The kind decides what of yours replaces it.

KindIn the referenceIn your video
title_cardWords on a plain or lightly textured backgroundA short line in your words
kinetic_typeWords that are the motion: typing, sliding, scalingYour headline, animated the same way
logoA brand mark on its own, usually a revealYour logo
ui_screenA whole product screen, flat to the cameraA screenshot or recording of your product
ui_closeupOne part of a screen enlarged: a button, a field, a cursorThe matching detail of your UI
deviceA screen inside a phone, laptop or browser frameYour screen in the same frame
chartA graph, counter or data graphic drawing inYour real numbers, never invented ones
characterA mascot, illustrated figure or avatarYour own mascot, or a placeholder
product_renderA physical product, photographed or in 3DYour product photo or render
live_actionFilmed footage of people or placesYour own footage, or a placeholder
collageSeveral images, cards or screens arranged togetherSeveral of your screens
abstractShapes, gradients, particles or lightThe same motion in your colours
end_cardThe closing frame: logo with a call to actionYour logo and call to action
blankAn empty frame held as a pauseThe same pause, nothing on screen

Entrances and motion

ValueMeaning
enters: cutHard cut: the whole picture changes in one frame.
enters: transitionAnimated transition: several frames of heavy change join two pictures (wipe, zoom, morph or dissolve).
enters: holdSame scene: motion resumes after the picture held still.
enters: blank_blackPasses through an empty black frame.
enters: blank_whitePasses through an empty white frame.
motion: stillUnder 0.4% of the frame moves.
motion: lowUnder 3%.
motion: mediumUnder 12%.
motion: high12% or more.

What the check catches before you ship

kuchi_check_remake takes the shot list GitHub Copilot CLI built: each shot's start and end in seconds, the reference_shot it rebuilds, how it enters, every line of on-screen text, and where each asset came from (user, generated, stock, placeholder or reference). It returns passed, errors and warnings by shot, and compare_frames.

  • Text that carries over the reference's brand, product names or slogans.
  • Any asset taken from the reference video: footage, UI, characters or music.
  • Generated logos or generated product UI, which should always come from you.
  • Placeholders still on screen.
  • Gaps or overlaps in the timeline, and shots whose length or entrance drifted from the reference shot they rebuild.

The check reads the shot list, not the file: the video never leaves your machine. GitHub Copilot CLI then renders a still at each compare_frames time and sets it beside the reference storyboard, which catches layout drift a quick watch misses.

Troubleshooting GitHub Copilot CLI

SymptomFix
The add command failsUse --transport http.
Edits to the config file are ignoredRestart Copilot CLI.
Commands are blockedApprove them for the folder.
No toolsCheck with /mcp.
The tool list is empty or the connection times outCheck that nothing on your network (a proxy, VPN or firewall) blocks HTTPS to kuchi.kalarislabs.com, and that the URL ends in /mcp.
A tool says the catalog is temporarily unavailableThe library is refreshing. Retry in a minute; nothing on your side needs to change.

Launch video templates to start from

All launch videos →
01:19
Launch date ·
9.65M Impressions
1.06MVideo plays
00:45
Launch date ·
5.15M Impressions
2.18MVideo plays

Components GitHub Copilot CLI can install

All components →

GitHub Copilot CLI and Kuchi: questions

How do I add an MCP server to GitHub Copilot CLI?

Run copilot mcp add --transport http kuchi https://kuchi.kalarislabs.com/mcp, or type /mcp add in a session. Servers are saved in ~/.copilot/mcp-config.json.

Is this the same as Copilot in VS Code?

No. VS Code has its own guide on this site with a one-click install. Copilot CLI is configured separately.

Is Kuchi free to use with GitHub Copilot CLI?

Yes. The Kuchi MCP server is open: no account, no API key and no payment. Your own agent plan applies as usual.

Will my video copy the reference?

No. A remake borrows the reference's timing, motion and layout. Every logo, screen, line of copy and asset on screen comes from your product.