# latent-spaces/brag > An agent skill (Claude Code, Codex, opencode, etc.) that turns a project you just built into a short launch video with music, motion, and share copy — in one command. Rendering is powered by Hyperframes. - Magnitude: 4.0 out of 10 — Steady - Stars: 18,376 total · Not enough measurements today - Star trust: star growth looks organic - Category: AI agents · Language: Python · License: MIT · Created: 2026-06-16 · Last push: 2026-10-23 - GitHub: https://github.com/latent-spaces/brag · Homepage: https://latent-spaces.github.io/brag/ · Page: https://gitnova.dev/en/r/latent-spaces/brag ## Useful for - Generate a brag.mp4 launch video for a fresh project with one agent command - Set the video tone with --tone, e.g. a 2016 startup launch parody - Enable voiceover narration via --voice using Kokoro ## Why it’s here - There are not enough fresh counter measurements for today's UTC day. The gain is unknown. - About 43 forks a day — people are taking the code. - Recent forks include notable developers: @LucNIK (218 followers). ## 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: 1,403 - Issues and pull requests: 69 - Watchers: 64 - Average over the last week: 261 per day - Usual pace: 284 per day - Latest release: v0.5.0 (2026-10-23) ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-05 … 2026-11-03: 218, 203, 195, 329, 349, 213, 269, 264, 236, 209, 185, 197, 188, 237, 235, 200, 161, 317, 493, 214, None, None, None, None, None, None, None, None, None, None ## Magnitude by day, last 14 days 10-12 3.7, 10-13 3.6, 10-14 3.5, 10-15 3.4, 10-16 3.5, 10-17 3.3, 10-18 3.6, 10-19 3.8, 10-20 3.6, 10-21 3.6, 10-22 3.4, 10-23 4.4, 10-24 4.7, 10-25 4.0 --- 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 2026-10-25 00:19 UTC, updated every 30 minutes.