Hash-verified video description sidecars for AI agents
cdaf stores a plain-text description beside a video and verifies the sidecar with SHA-256 and byte size before allowing agents to use it.
From Github Awesome — GitHub Trending Weekly #47: utopia, neo, slotstream, Codewhale, TokensBurned, mono-color-skill at 13:18
Problem: Agents waste tokens reanalyzing unchanged footage and can accidentally use stale descriptions.
For: AI systems repeatedly analyzing the same video files.
Products from this video
ABYSSAL cc-prune CDAF (Cached Descriptive Asset Files) Codewhale defragger Editable Visual Design FixAnything genart-skill h3-storyboard-skill HexStellar hqtui Keyword Pro LightNav-0 loadersz markdown-graphs Monocolor Editorial Print Noty Omakade Procedura qwen38-27b-rtx3090 Shrimply Skill Cabinet SkillRadar skin-tokens.cpp slotstream Strata TokensBurned TrustMeBro Utopia vol-rs
Examples
- Sidecar analysis versus direct video analysis: the named benchmark comparison.