Natural-language video search
Search a video library by describing a person, place, scene, object, action, concept, topic, or moment in plain language. Results map back to the exact moment in the source video.
Jockey
Jockey is TwelveLabs’ video intelligence agent for searching, organizing, and assembling content across a video library. It supports natural-language video search, structured extraction, and chat-based access through Claude, with API and SDK options for developers.
Overview
Jockey is TwelveLabs’ video intelligence agent for searching, organizing, and assembling content across a video library. The page describes it as a research preview and positions it as an agent layer for video understanding built on TwelveLabs’ Marengo and Pegasus models.
It is designed to work with both human-led workflows and developer integrations. On the page, marketing teams use it to label and compare ad footage, creators use it to search archives and pull highlight reels, and developers can access the same underlying video understanding through API and SDK tools.
Core capabilities
Chat-based library access
Connect the product to Claude through the MCP endpoint shown on the page and ask questions directly inside the chat interface. The page also says ChatGPT support is coming soon.
Structured data extraction
Run structured extraction from video by defining a JSON schema and receiving timestamped metadata back. The page describes this as machine-readable output for every video.
Multimodal retrieval support
Use multimodal embeddings across video, image, audio, and text to support retrieval and ranking. The pricing and product pages present this as part of the broader TwelveLabs video understanding stack.
Video analysis and text generation
Generate summaries, chapters, highlights, and other text outputs from video through the adjacent TwelveLabs platform. The product overview page ties these capabilities to search, analyze, and embed workflows.
Frame-accurate timestamps
Deep-link from search results into the exact playback moment using frame-accurate timestamps. This helps users move from discovery to review without manually scanning clips.
Common use cases
Ad library review for marketing teams
Search a creative library for every ad featuring a creator, spokesperson, logo, hook, format, or tone, then compare patterns across campaigns before planning the next shoot.
Archive search for creators
Ask questions about an archive in plain language, find exact clips instead of folders, and pull line-level references to quotes or moments you have already captured on camera.
Highlight reel assembly
Turn a topic into an edit-ready highlight reel by pointing Jockey at a subject and reviewing the returned moments for a fast first pass on a cut.
Developer-facing video search
Embed video understanding into a product with API and SDK tools, then use natural-language search, structured extraction, and timestamped metadata in your own workflow.
Chat-based library lookup
Connect a video or photo library to Claude and retrieve a person, place, scene, or moment directly inside chat without learning a new interface.
Pros and Cons
Pros
- Combines search, analysis, and assembly around one video library workflow.
- Supports plain-language queries against people, places, scenes, objects, actions, concepts, topics, and moments.
- Provides timestamped results and frame-accurate links back to playback.
- Can connect into Claude through the MCP endpoint shown on the page.
- Backed by TwelveLabs’ Marengo and Pegasus models, which the site presents as the foundation for video understanding.
Cons
- The product is in research preview and the site says it is accepting limited sign-ups.
- Some integration coverage is still limited on the page; for example, ChatGPT is listed as coming soon.
FAQ
What is Jockey used for?
Jockey is positioned as a research-preview agent for video understanding. The site says it is for organizing, searching, and assembling across a video library, and it can be used in Claude through the listed integration flow.
Is there a free plan or trial?
The site shows a free trial-style entry point and says it is currently accepting limited sign-ups. The pricing page also indicates a Free plan is available without a credit card, with a Developer pay-as-you-go plan and Enterprise contracts.
What integrations are available?
The rendered page shows an MCP endpoint for connecting a library inside Claude, and it also says ChatGPT is coming soon. The product overview and developer hub pages support API-based use as well.
Who is Jockey aimed at?
The page highlights use in Claude, API and SDK access, and workflows such as natural-language search, structured data extraction, and frame-accurate results. It also notes that the product is in research preview, so availability is limited.
What kind of outputs can it produce?
The source shows input video is analyzed and results can return timestamped metadata, summaries, highlight reels, and edit-ready outputs. It does not provide a full list of supported export formats on the page.
Quick Facts
- Category
- Video intelligence agent
- Primary users
- Marketing teams, creators, and developers
- Platform
- Web, Claude integration, API, and SDKs
- Availability
- Research preview with limited sign-ups
- Pricing shape
- Free plan, Developer pay-as-you-go plan, and Enterprise contracts
- Models
- Built on Marengo and Pegasus
Alternativas ao Jockey
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
Ably Chat
Ably Chat is a chat API platform for building custom realtime chat applications. It supports room-based messaging, typing indicators, presence, reactions, and message updates, with usage-based pricing options for different deployment stages.
Manta AI
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.
Falconer
Falconer is an AI-powered company brain that keeps internal documentation accurate, searchable, and up to date by syncing with tools like GitHub, Slack, and Linear. It helps engineering and cross-functional teams centralize knowledge and answer questions from a shared source of truth.