# HaD0Yun/CozyClay > Open-source previs tool in the browser: block a scene in 3D, pose characters, author camera moves and cuts, then hand the shot to an AI video model. For people making AI video who want to lock staging, timing and camera cheaply first. - Magnitude: 0.8 out of 10 — Cooling - Stars: 1,845 total · +0 stars measured 2026-11-16, 00:32–09:44 UTC, ≈ 1 by evening - Star trust: star growth looks organic - Category: Generative media · Language: JavaScript · License: AGPL-3.0 · Created: 2026-07-28 · Last push: 2026-11-16 - GitHub: https://github.com/HaD0Yun/CozyClay · Homepage: https://cozyclay.org · Page: https://gitnova.dev/en/r/HaD0Yun/CozyClay ## Useful for - Block a scene and character motion in 3D before generating video - Export first frame, greybox clip and prompt for an AI video model - Drive the scene from Claude Desktop or Cursor via the MCP server ## How to get started ```sh npx cozyclay ``` Copied as is from the “quick start” section of the README. GitNova has not run these commands: check them in the original before running: https://github.com/HaD0Yun/CozyClay#readme ## Why it’s here - Star-counter measurements on 2026-11-16 (UTC), 00:32–09:44: 1845 → 1845 stars (+0). This is the change over that interval. - Estimated end-of-day forecast: about +1 stars, using observed gains and the previous day. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 201 - Issues and pull requests: 1,315 - Watchers: 23 - Average over the last week: 33 per day - Usual pace: 29 per day - Stars in the last hour (measured): 0 - Latest release: windows-installer (2026-11-12) ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-18 … 2026-11-16: 5, 29, 45, 18, 47, 36, 26, 69, 39, 21, 16, 43, 95, 11, 88, 18, 66, 5, 57, 9, 9, 6, 63, 80, 7, 60, 0, 79, 3, 0 ## Magnitude by day, last 14 days 11-02 3.5, 11-03 2.6, 11-04 3.0, 11-06 2.4, 11-07 1.5, 11-08 1.4, 11-09 2.0, 11-10 3.0, 11-11 2.9, 11-12 2.0, 11-13 2.7, 11-14 2.3, 11-15 2.9, 11-16 0.9 ## More in this category 1. **n4ze3m/tiny-voca** — 6.9 · Early signal · Generative media · Python · +138 stars measured 2026-11-16, 00:28–09:36 UTC, ≈ 353 by evening tiny-voca is a small English text-to-speech model with two voices (F2 and M2), 4.5M parameters, trained from scratch. It runs on CPU, in PyTorch, ONNX Runtime and in the browser. Full card: https://gitnova.dev/en/r/n4ze3m/tiny-voca.md 2. **haziqahmedqasmi/PeakCut** — 6.6 · Early signal · Generative media · Python · +56 stars measured 2026-11-16, 00:28–09:36 UTC, ≈ 170 by evening Self-hosted Python service that turns long videos and live streams into 9:16 vertical clips with captions and a hook, using your own AI key. Aimed at streamers and editors who need to cut content. Full card: https://gitnova.dev/en/r/haziqahmedqasmi/PeakCut.md 3. **Moh4696/cinematic-skill** — 5.3 · Early signal · Generative media · Python · +41 stars measured 2026-11-16, 00:28–09:36 UTC, ≈ 105 by evening A skill for coding agents that writes, narrates and assembles a documentary film entirely from code: one continuous camera move over photos, maps and cards, timed to the voice. Every frame is drawn with Skia in Python rather than… Full card: https://gitnova.dev/en/r/Moh4696/cinematic-skill.md 4. **higurashi-ai/Haru** — 4.6 · Early signal · Generative media · Python · +38 stars measured 2026-11-16, 00:28–09:36 UTC, ≈ 98 by evening Inference code for Haru-4B, a multilingual full-duplex spoken dialogue model that listens and speaks at the same time, like on a phone call. Includes PyTorch, MLX and vLLM-Omni implementations plus a web demo. Full card: https://gitnova.dev/en/r/higurashi-ai/Haru.md 5. **TensaikunYT/Videohub** — 4.6 · Early signal · Generative media · JavaScript · +19 stars measured 2026-11-16, 00:28–09:36 UTC, ≈ 62 by evening Local review studio and render queue for videos written as code by coding agents like Claude Code or OpenCode: live preview from the film page, frame annotations, fixes and render queue. Full card: https://gitnova.dev/en/r/TensaikunYT/Videohub.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-11-16 09:47 UTC, updated every 30 minutes.