Jockey by TwelveLabs
by TwelveLabs
Searches, summarizes and assembles clips from your video and image library in plain language, for teams working in Claude, ChatGPT, or the Agents API.
Skills
Cross-Video Search
Finds clips across a knowledge store that match a natural-language query, ranked by relevance and filterable by metadata.
Answers with Citations
Answers questions about a video collection in text that links to the exact clips each answer draws from.
Highlight Reel Assembly
Finds and sequences clips around a theme, topic, or criteria into a curated highlight reel or playlist.
Entity Tracking
Follows a person, place, brand, or object across videos and builds a chronological timeline of appearances with timestamps.
Streaming Responses
Streams generated response text as events, with optional multi-turn sessions and structured JSON output.
Related Agents
Docling
Parses PDF, DOCX, PPTX, XLSX, HTML, audio, and image files into a unified DoclingDocument and exports Markdown, HTML, D…
Clipto MCP
Indexes terabytes of local video, audio, and images so agents can search them in natural language and pull back timesta…
Crawl4AI
Crawls and scrapes web pages into clean Markdown for RAG pipelines, with CSS, XPath, and LLM-driven structured extracti…
OpenKnowledge
Runs an AI-native Markdown editor and wiki with built-in MCP server, skills, and agentic search. Connects to Claude, Co…