VMAFx
GPU-accelerated perceptual video quality assessment toolkit
Visit vmafx.github.io ↗What is VMAFx?
VMAFx is an open-source fork of Netflix's VMAF that measures perceptual video quality with hardware acceleration and SIMD optimization. It maintains byte-for-byte compatibility with upstream reference scores while adding production-ready features like CUDA, SYCL, HIP, and Metal GPU backends, plus NEON and SVE2 SIMD support.
The toolkit serves video engineers and codec developers who need accurate quality metrics in pipelines. It includes a command-line tool, Python library, FFmpeg integration, C API, and cloud-native deployment options. The project was developed using AI coding tools including Claude Code.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered VMAFx automatically. Evidence: GitHub VMAFx/vmafx; repo has .claude, .codex, .cursor. View source.
Similar vibe-coded apps
Local context engine that prepares task-focused file packs for AI coding agents
Prescriptive methodology and agent skills for spec-driven development with AI
Browser and desktop 2.5D + 3D CAD/CAM workspace for CNC machining
Shared persistent memory for AI coding tools across sessions and applications
In-browser behavior tree execution engine for AI agents at ~60Hz
Zero-config Docker ingress router with automatic TLS provisioning
Encrypted secret manager CLI that hides API keys from AI agents