Show HN: A personal creative room where an idea turns into a short film

A full-stack engineer released Kiteva, a source-available desktop application for macOS that turns a written idea into a short motion-graphics film by orchestrating Anthropic's Claude Opus 5.5 or OpenAI's GPT-6.1 Sol, under a non-commercial license based on MIT that adds a no-commercial-use condition and is not OSI-approved. Kiteva reads user references into a structured brief, has the main model propose a dozen or more directions drawn from summaries of 136 Motion Graphics, scores them with Typesafe's JEV evaluator, renders silent 3-second previews, then produces a full film at 1080p or 1440p, 30 or 60 fps, up to 5 minutes, with optional lyrics and local Kokoro or Pocket TTS narration. Every render is probed with ffprobe and fully decoded, with layout and contrast checks via the HyperFrames renderer or frame-consistency checks via the Multiplane trial, and the author's demo film was a 28-second run.

A personal creative room where an idea turns into a short motion-graphics film. Runs on your Mac with Claude Opus 5.5 https://platform.claude.com/docs/en/about-claude/models/overview or GPT-6.1 Sol https://developers.openai.com/api/docs/models/gpt-6.1-sol . English · 简体中文 https://github.com/delexw/kiteva/blob/main/README.zh-CN.md <sub This film was made in Kiteva, from one real run: 28 seconds with local Kokoro narration and a music bed the film agent wrote in code. Above is a silent 14-second loop from the middle; click it for the full MP4 with sound. How it was made https://github.com/delexw/kiteva/blob/main/docs/intro-video.md .</sub Important Non-commercial license. Kiteva's source is shared under the Kiteva Non-Commercial License https://github.com/delexw/kiteva/blob/main/LICENSE . It's based on MIT but adds a no-commercial-use condition, so it's source-available and not an OSI-approved open source license. Third-party parts keep their own licenses. See License license . I'm not a professional designer. I'm a full-stack engineer working on content and creative tools, and along the way I picked up a few creative ideas. Then I noticed Opus 5.5 https://platform.claude.com/docs/en/about-claude/models/overview has a real feel for this kind of work. There's an internal hackathon coming up at my company, and I just find these motion effects fun, so I started collecting motion pieces that had that certain something, along with notes on what technology could make each one. The pile got big. So I built an agent to put that collection and Opus 5.5 to work, to see how far it could go. The results surprised me, so I'm sharing the agent's source here, under non-commercial terms. I collected a lot. Some of it is dazzling, and some of it is probably wrong. I kept it all anyway 😄 Opus 5.5 is my favourite for the creative part. The Codex https://developers.openai.com/codex provider with GPT-6.1 Sol https://developers.openai.com/api/docs/models/gpt-6.1-sol is wired up too, and I'm trying it out for fun. You choose the provider per project. Idea → brief → Motion Graphic combinations → previews → full film → review and delivery <sub The room right after the intro film finished. The Assistant starts a new idea; each project lives in its own widget.</sub - A desktop-style room. Everything happens in windows on a personal desktop: an assistant that walks you through the idea, documents, images, websites, music and lyrics, and settings, plus a material shelf and one widget per project. Nothing calls a model until you press Create . - A brief from your references. A small model reads your files and, if you add websites, opens them in a fresh headless Chromium https://www.chromium.org browser to take screenshots. It writes a structured brief and then checks it. - Motion Graphic combinations. The main model reads summaries of all 136 Motion Graphics and proposes a dozen or more directions. Each pairs one primary Motion Graphic with supporting ones. A separate evaluator, Typesafe https://docs.typesafe.ai 's JEV https://docs.typesafe.ai/models , scores them and keeps the number of directions you asked for 1–5 . - Silent 3-second previews of the same story beat, one per direction, so you can compare. - The full film continues the preview session you picked, at 1080p or 1440p, 30 or 60 fps, up to 5 minutes, with optional on-screen lyrics and local narration Kokoro https://huggingface.co/hexgrad/Kokoro-82M or Pocket TTS https://pypi.org/project/pocket-tts/ . - Review and delivery. Every render is probed with ffprobe and fully decoded. With HyperFrames https://github.com/heygen-com/hyperframes , the default renderer, layout and contrast checks run too, and findings are repaired in focused rounds. The Multiplane https://github.com/LBEILC/Multiplane trial skips those two checks and verifies frame consistency instead. A small model then reviews the result. You get an MP4, a poster, a project ZIP, a playback copy and a Storyboard. | <sub Explore all 136 Motion Graphics. Each card plays a reviewed 3-second demo.</sub | <sub The two directions Kiteva previewed for the film above. I picked Paper Room.</sub | <sub The intro film's own Storyboard, caught during scene 2 of 9.</sub Every preview and film saves a STORYBOARD.json with timed scenes, beats, captions and audio notes that match the actual composition. The Storyboard page plays it back as a little behind-the-scenes rehearsal. A stick-figure director and crew stagehand, lighting, lettering, sound, camera walk to their marks when a beat calls for their job, and you can play, replay or scrub through the film's timeline. To be honest about what it is: the crew is a playful reading of the recorded cues, not real production staff and not a live render monitor. Live progress is in each project's activity lines in the room. And it has nothing to do with the UI-component tool called Storybook https://storybook.js.org . | Motion Graphics | 136 assets/catalog/video-style-catalog.json | | Motions | 46 assets/catalog/motion-pattern-catalog.json | | Technology pool entries | 92 recommendations across visual construction, motion, rendering and supporting tools | | Bundled authoring skill | 1 Anatomy https://github.com/wheresryan22/anatomy | | Renderers | HyperFrames https://github.com/heygen-com/hyperframes default , Multiplane https://github.com/LBEILC/Multiplane trial , Remotion https://www.remotion.dev fallback only | Combinations are where it gets interesting. A direction can mix one primary Motion Graphic with supporting ones 1–3 in total for films under 30 seconds, up to 6 for films over three minutes , and the model picks motions and technologies to suit. That gives far more starting points than any single style. It doesn't promise that every combination works. Some won't, which is why there are previews, an evaluator and repairs. | Job | Claude projects | Codex projects | |---|---|---| | Brief, reference checks, Motion Graphic summaries, lyrics, result review, simple repairs | Claude Haiku 5.5 https://platform.claude.com/docs/en/about-claude/models/overview | GPT-6 Luna https://developers.openai.com/api/docs/models/gpt-6-luna | | Combination proposals, previews, the full film, pacing/style repairs | Claude Opus 5.5 https://platform.claude.com/docs/en/about-claude/models/overview | GPT-6.1 Sol https://developers.openai.com/api/docs/models/gpt-6.1-sol | | Scoring and choosing directions | JEV https://docs.typesafe.ai/models via Typesafe https://docs.typesafe.ai | JEV https://docs.typesafe.ai/models | | Recording every call, token count and cost estimate | Governance report | Governance report | More detail, including the workflow diagrams, is in docs/architecture.md https://github.com/delexw/kiteva/blob/main/docs/architecture.md . You need macOS, Node.js https://nodejs.org 24+, Chrome https://www.google.com/chrome/ or Chromium https://www.chromium.org , and FFmpeg https://ffmpeg.org with ffprobe . Then two kinds of access: - A model provider, by API key or by an existing signed-in subscription. For Claude, set ANTHROPIC API KEY or CLAUDE CODE OAUTH TOKEN , or just be signed in to Claude Code https://code.claude.com/docs/en/overview on this Mac. For Codex, set CODEX API KEY or OPENAI API KEY , or be signed in to the Codex CLI https://developers.openai.com/codex ~/.codex/auth.json . Subscriptions work, but I haven't tested how subscription usage or remaining percentage is reported. - JEV https://docs.typesafe.ai/models , configured separately. Put TYPESAFE API KEY in .env.local . It's needed whenever Kiteva generates directions. Picking Motion Graphics yourself skips it. git clone https://github.com/delexw/kiteva.git cd kiteva npm ci cp .env.example .env.local add TYPESAFE API KEY provider keys are optional if you're signed in npm run build npm start open http://127.0.0.1:4317 Optional: npm run speech:setup Kokoro https://github.com/thewh1teagle/kokoro-onnx or npm run speech:setup:pocket Pocket TTS https://pypi.org/project/pocket-tts/ for local narration. They need Python https://www.python.org 3.10–3.13. For UI development, keep the backend running and use npx vite Vite https://vite.dev , http://127.0.0.1:4319 . The catalogs, reviewed artwork and 136 preview clips ship with the repo, so browsing costs nothing. Your projects, uploads, room layout, databases and credentials stay in Git-ignored folders on your machine. | Part | What it is | Status | |---|---|---| | Anatomy https://github.com/wheresryan22/anatomy | Isometric technical-illustration skill and drawing kit 3D mode is beta | The one bundled skill. 141 files pinned to e9488296 , SHA-256 checked, MIT, unchanged | | HyperFrames https://github.com/heygen-com/hyperframes 0.8.144 | HTML video composition and export | npm dependency, pinned, default renderer | | Multiplane https://github.com/LBEILC/Multiplane 0.3.10 | render t shot renderer with motion blur | npm dependency, pinned, trial setting | | Remotion https://www.remotion.dev 4.x | React video renderer | npm dependency, fallback only has its own license terms | | reference browser / capture video | Headless website inspection, screenshots and walkthrough recording via Puppeteer https://pptr.dev | Built into Kiteva, for both providers | | Kokoro https://github.com/thewh1teagle/kokoro-onnx , Pocket TTS https://pypi.org/project/pocket-tts/ | Local narration | Python set up by npm run speech:setup . Weights downloaded to Git-ignored models/ | | Claude Agent SDK https://github.com/anthropics/claude-agent-sdk-typescript , Codex SDK https://github.com/openai/codex/tree/main/sdk/typescript , @typesafe-ai/sdk https://docs.typesafe.ai/sdk/javascript | Model providers and JEV | npm dependencies | | Caveman https://github.com/JuliusBrussee/caveman | Local token-compression proxy for SDK calls | npm dependency, on by default | | GSAP https://gsap.com , Three.js https://threejs.org , PixiJS https://pixijs.com , Paper.js http://paperjs.org , Rough.js https://roughjs.com , Motion https://motion.dev , chroma.js https://gka.github.io/chroma.js/ , Pica https://github.com/nodeca/pica | Drawing and motion libraries offered to generated films | npm dependencies | | React https://react.dev , Ant Design https://ant.design + Ant Design X https://x.ant.design , Radix https://radix-ui.com , Tailwind CSS https://tailwindcss.com , Vite https://vite.dev , Fastify https://fastify.dev , Zod https://zod.dev | App UI, server and shared contracts | npm dependencies | | FFmpeg https://ffmpeg.org , Chrome https://www.google.com/chrome/ / Chromium https://www.chromium.org , Python https://www.python.org , Blender https://www.blender.org optional | External tools | Not bundled. You install them | Being in the 92-entry technology pool doesn't mean a library is installed. Twelve pool entries are recommendations only, and generation can't install packages or use the network. The full list with a status for every entry, plus all 75 direct npm dependencies, is in docs/technology-pool.md https://github.com/delexw/kiteva/blob/main/docs/technology-pool.md . From Kiteva's own governance report snapshot 2026-10-17, app pricing date 2026-10-13 , my three earlier development projects all Claude, 90–120 s films, five preview directions each came to $16.46, $18.73 and $37.42 in SDK-estimated, API-equivalent model usage. More than 90 % of input tokens were cache reads. Nearly all of the cost is Opus writing previews and the film. Haiku's preparation and review work cost cents, and JEV ranking under a cent. The expensive one regenerated its directions and needed nine repair calls. That's three projects, not a benchmark or a per-minute price. Local compute render time, electricity isn't priced, and there's no GPT-6.1 Sol example yet. These are token counts priced at API rates. If you're signed in with a subscription instead of an API key, they are not your bill and not a meter of your plan's allowance. I haven't tested subscription usage or remaining-percentage reporting. Method and caveats: docs/costs.md https://github.com/delexw/kiteva/blob/main/docs/costs.md . - macOS only for now the render sandbox uses sandbox-exec . Single user, local only. - Multiplane https://github.com/LBEILC/Multiplane is a trial: one sound file, no video clips inside scenes, and no automatic layout or contrast checks frame consistency is still verified . - Remotion https://www.remotion.dev is a fallback, not a setting, and its renders skip the HyperFrames layout/contrast checks too. - No generated singing, image generation or stock footage. Visuals are drawn in code, or come from your uploads and website captures. - The catalog is my personal collection. Some descriptions or technology suggestions may be off. Issues are welcome. - Generation takes a while, often many minutes per preview, and uses real API credit or subscription usage. - Architecture https://github.com/delexw/kiteva/blob/main/docs/architecture.md : components, workflow, renderers, capture, skills, storage Mermaid diagrams - Technology inventory https://github.com/delexw/kiteva/blob/main/docs/technology-pool.md : all 92 pool entries, the bundled skill, renderers, TTS and every dependency - Costs https://github.com/delexw/kiteva/blob/main/docs/costs.md : how the governance numbers are computed - Intro film provenance https://github.com/delexw/kiteva/blob/main/docs/intro-video.md : how the film above was made in Kiteva - README references https://github.com/delexw/kiteva/blob/main/docs/readme-references.md : open projects whose READMEs I learned from - Application guide https://github.com/delexw/kiteva/blob/main/docs/application-guide.md · Speech setup https://github.com/delexw/kiteva/blob/main/docs/speech.md · Multiplane trial https://github.com/delexw/kiteva/blob/main/docs/multiplane-trial.md Bug reports, catalog corrections and focused PRs are welcome. See CONTRIBUTING.md https://github.com/delexw/kiteva/blob/main/CONTRIBUTING.md for setup, the checks to run npm run lint , npm test , npm run build , the creative quality bar seekable compositions, real rendered frames and third-party rules. Kiteva's own code, catalogs and docs are © 2026 Yang Liu @delexw https://github.com/delexw , licensed under the Kiteva Non-Commercial License https://github.com/delexw/kiteva/blob/main/LICENSE . In short: you may use, copy, modify and share it for non-commercial purposes, such as personal projects, learning, research and evaluation, with the notice kept. Internal, non-production evaluation inside an organisation, like trying it at an internal hackathon, counts as non-commercial. Selling it, offering it as a paid service, using it for paid client work, or putting what you make with it into commercial production needs separate permission. Ask in an issue. This summary isn't legal advice, and the LICENSE text is what applies. Bundled and dependent software keeps its own license: Anatomy https://github.com/wheresryan22/anatomy MIT , HyperFrames https://github.com/heygen-com/hyperframes and Multiplane https://github.com/LBEILC/Multiplane Apache-2.0 , Remotion https://www.remotion.dev/license Remotion License , GSAP https://gsap.com/standard-license GSAP Standard License and the rest as listed in docs/technology-pool.md https://github.com/delexw/kiteva/blob/main/docs/technology-pool.md . Model providers, speech models and other services have their own terms.