Status basis: npm_downloads_7d momentum fell to 0 per 3d from 131 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 131 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 160 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -13 per 3d from 173 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 131 in the last 3d vs 29 in the 3d before (ratio 4.5x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to -13 per 3d from 173 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 160 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Anomaly daily change 144.0 is 9.7 standard deviations from this entity's own prior mean (-13.2±16.2, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change 144.0 is 9.7 standard deviations from this entity's own prior mean (-13.2±16.2, baseline excludes this point) — unusual, not necessarily adoption
- first observed Kanon started keeping permanent history for this agent
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | — | unknown | — |
| Bring your own key | — | unknown | — |
| Autonomy level | 2 | inferred | 1 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | mcp,gemini,openai,ffmpeg,whisper | inferred | 2 quote(s) |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
It extends AI’s capabilities beyond text and images, providing a key building block for video understanding and advancing AI agents’ perceptual abilities.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“extracts frames via ffmpeg and processes audio via multiple backends”— readme
“processes audio via multiple backends (Gemini API, local Whisper, or OpenAI API)”— readme
“MCP server downloads it with yt-dlp”— readme
FAQ
What is claude-video-vision?
claude-video-vision is a plugin for Claude Code that allows AI to analyze videos by extracting frames and interpreting audio, enabling video comprehension similar to human viewing.
What does claude-video-vision do?
Allow AI to automatically watch and interpret video content, including extracting key frames, recognizing speech, and understanding visual context.
Why does claude-video-vision matter?
It extends AI’s capabilities beyond text and images, providing a key building block for video understanding and advancing AI agents’ perceptual abilities.
How much does claude-video-vision cost?
Free
Is claude-video-vision free?
Yes — claude-video-vision has a free tier. Pricing as stated on its own page: Free
Is claude-video-vision open source?
Yes — claude-video-vision is open source.
What does claude-video-vision integrate with?
mcp,gemini,openai,ffmpeg,whisper
How popular is claude-video-vision?
As tracked by KanonAgent: 25 upvotes (first indexed 2026-08-08).
What are the best claude-video-vision alternatives?
Similar AI agents tracked by KanonAgent: open-design, Agent-Reach, deer-flow, ruflo, career-ops, archify.