latent-spaces/brag

You built it. Now brag. Turn the project you just created into a short, shareable launch video with one command.

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 40 minutes ago
Added to GitGenius on September 18th, 2026
Created on June 16th, 2026
Open Issues & Pull Requests: 4 (+0)
GitHub issues: Enabled
Number of forks: 326
Total Stargazers: 5,352 (+0)
Total Subscribers: 22 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 3.6 days
Mean response time: 2.8 days
90th percentile: 4.8 days
Tracked items: 5

Most active contributors

Sign in to see contributor activity.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 1
New in 7 days: 1
Closed in 7 days: 0
Avg open age: 0 days
Stale 30+ days: 0
Stale 90+ days: 0

Recent activity

Opened in 7 days: 1
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Brag is an agent skill that automatically generates short, shareable launch videos from project repositories with a single command.

The tool solves the problem of creating compelling promotional content for newly built projects. It works by analyzing a project's structure and purpose, then using Claude to craft a narrative arc—deciding the product angle, tone, and which moments to highlight. This story brief is handed to Hyperframes, which handles video composition, timing, and rendering. The output includes the underlying plan, a composition brief, share copy, and a finished MP4 file. Voiceover narration via Kokoro is available as an optional feature.

Brag is designed for developers who want to quickly showcase their work without manual video production. It suits any project that can be visually represented—the tool works by examining what exists in a repository and turning it into a narrative. The skill integrates with multiple agent platforms including Claude Code, opencode, Codex CLI, and any agent supporting custom instructions, making it accessible across different development environments. Installation is straightforward via the skills CLI or by copying the skill directly to an agent's discovery path.

The project maintains active engagement with contributions and feature requests welcomed through issues and pull requests. Development includes careful attention to cross-platform compatibility, with explicit guidance for Windows users regarding symlink configuration and fallback copy procedures. The codebase is organized to support multiple agent discovery mechanisms simultaneously through symlinks, reducing friction for users across different tools.