Monitor an IP camera stream for specific events and get alerted.
Generate highlight clips automatically from long recordings.
Add subtitles and transcripts to a video automatically.
Capture a screen recording session and write a report about what happened.
| video-db/skills | italozucareli/zabbix-observability | lllyasviel/singlefiledb | |
|---|---|---|---|
| Stars | 84 | 85 | 85 |
| Language | Python | Python | Python |
| Last pushed | — | — | 2023-11-24 |
| Maintenance | — | — | Dormant |
| Setup difficulty | moderate | moderate | easy |
| Complexity | 3/5 | 3/5 | 2/5 |
| Audience | developer | ops devops | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires connecting to the VideoDB server-side platform.
VideoDB Skills is a plugin for AI coding agents like Claude Code, Cursor, and Copilot that gives them the ability to work with video. Without something like this, an AI agent has no reliable way to upload, process, search through, or edit video content because doing so typically requires stitching together complex tools like ffmpeg and various cloud services. The skill connects to VideoDB, a server-side video platform, and exposes a consistent set of capabilities through a single interface. The agent can ingest video from YouTube URLs, local files, RTSP streams (the kind of stream many IP cameras broadcast), and direct desktop screen capture with audio. Once video is ingested, the agent can search through it by spoken words or visual scenes to find specific moments, generate timestamped transcripts and subtitles, cut and merge clips, add overlays and background music, dub or translate audio, and get back a playable HLS streaming link for anything it creates. HLS (HTTP Live Streaming) is a standard format that lets you play video in any browser without special software. A developer would use this when building an AI-powered application that needs video understanding without managing encoding infrastructure directly. Example use cases from the README include monitoring an IP camera for specific events, creating highlight clips from long recordings, adding subtitles automatically, or capturing a screen session and writing a report about what was happening. The tech stack is Python 3.9 or later.
A plugin that gives AI coding agents the ability to ingest, search, edit, and stream video without managing encoding infrastructure directly.
Mainly Python. The stack also includes Python, VideoDB, HLS.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.