# Murea-Labs/InWorld > Open-source video generation with synchronized sound from text and reference images, plus the Murea-Mind agent that turns user actions into a continuing filmed story. - Magnitude: 3.2 out of 10 — Steady - Stars: 3,215 total · +116 stars measured 2026-11-16, 00:30–09:38 UTC, ≈ 240 by evening - Star trust: unusual star pattern (heuristic) - Category: Generative media · Language: Python · License: Apache-2.0 · Created: 2026-10-13 · Last push: 2026-10-20 - GitHub: https://github.com/Murea-Labs/InWorld · Page: https://gitnova.dev/en/r/Murea-Labs/InWorld ## Useful for - Generate a 1280×704 clip with dialogue and sound from a prompt and references - Continue an existing clip with the same characters and scene - Play an interactive story in the browser where each turn is filmed as a clip ## Why it’s here - Star-counter measurements on 2026-11-16 (UTC), 00:30–09:38: 3099 → 3215 stars (+116). This is the change over that interval. - Estimated end-of-day forecast: about +240 stars, using observed gains and the previous day. - The repository is 34 days old and already has 3,215 stars. - About 40 forks a day — people are taking the code. ## Star trust Unusual star pattern (heuristic). - Unusually even star flow: about 149 per day without the usual ups and downs. - Hardly anyone watches for updates: 0 watchers for 3,215 stars. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 449 - Issues and pull requests: 4 - Watchers: 0 - Average over the last week: 168 per day - Usual pace: 112 per day - Stars in the last hour (measured): 11 ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-18 … 2026-11-16: 11, 2, 12, 2, 0, 0, 62, 71, 171, 106, 131, 129, 132, 132, 141, 139, 134, 137, 133, 149, 153, 155, 156, 154, 156, 156, 155, 156, 158, 116 ## Magnitude by day, last 10 days 11-07 3.5, 11-08 4.0, 11-09 3.7, 11-10 3.7, 11-11 3.3, 11-12 3.7, 11-13 3.2, 11-14 3.2, 11-15 3.2, 11-16 3.2 ## Similar by description 1. **Pika-Labs/Pika-H3-Flex** — 1.3 · Cooling · Generative media · Python · +3 stars measured 2026-11-16, 00:36–09:43 UTC, ≈ 6 by evening Pika H3 Flex model for local inference of video generation with synchronized stereo audio in six sampling steps, supporting text, endpoint frames and multimodal references. Full card: https://gitnova.dev/en/r/Pika-Labs/Pika-H3-Flex.md 2. **HaD0Yun/CozyClay** — 0.8 · Cooling · Generative media · JavaScript · +0 stars measured 2026-11-16, 00:32–09:44 UTC, ≈ 1 by evening 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. Full card: https://gitnova.dev/en/r/HaD0Yun/CozyClay.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.