Jockey

A conversational video agent combining large language models with video processing APIs.

CommonProductVideoConversational AgentVideo Processing

Jockey is a conversational video agent built on top of Twelve Labs API and LangGraph. It integrates the capabilities of existing Large Language Models (LLMs) with Twelve Labs' API, utilizing LangGraph for task allocation to distribute the workload of complex video workflows to appropriate base models. LLMs are used for logically planning execution steps and interacting with users, while video-related tasks are passed to the Twelve Labs API powered by Video Foundation Models (VFMs) for native video processing, eliminating the need for intermediary representations like pre-generated captions.

Distributes the workload of complex video workflows by combining large language models with video processing APIs.
Utilizes LangGraph for task allocation
improving video processing efficiency.
Leverages LLMs to logically plan execution steps
enhancing user interaction experience.
Processes video tasks directly using video foundation models
eliminating the need for intermediary representations.
Supports customization and extension to adapt to diverse video-related use cases.
Offers terminal and LangGraph API server deployment options
flexibly catering to development and testing needs.

Jockey is geared towards developers and teams handling complex video workflows
particularly those looking to leverage large language models to enhance their video content creation and editing processes. It caters to professional users requiring high customization and automation in video processing tasks.

Video editing teams automate video clipping and caption generation using Jockey.
Content creators utilize Jockey to generate video drafts and storyboards.
Educational institutions employ Jockey to create interactive video tutorials.

1. Install necessary external dependencies such as FFmpeg
Docker
and Docker Compose.
2. Clone the Jockey GitHub repository to your local environment.
3. Create and activate a Python virtual environment

Visit

Jockey Visit Over Time

Monthly Visits

503747431

Bounce Rate

37.31%

Page per Visit

5.7

Visit Duration

00:06:44

Jockey Visit Trend

Jockey Visit Geography

Jockey Traffic Sources

Jockey Alternatives

OneGen — An efficient single-pass unified generation and retrieval framework suitable for large language models.

Programming•Natural Language Processing•Large Language Models

Open Source LLM Tools — A collection of open-source large language model tools.

Productivity•AI Tools•Open Source

PresentationGen — A SpringBoot Web application that utilizes large language models to generate PPT files.

Productivity•Automation•Presentation

Zion — No-code development platform for quickly building personalized applications.

ChineseSelection•No-code development•AI applications

144

Shire — An AI programming agent language that facilitates communication between large language models (LLMs) and integrated development environments (IDEs) for automated programming.

Programming•AI Programming•Automation

Draw an Audio — Utilizing multi-command video-to-audio synthesis technology

Music•Audio Synthesis•Video Processing

PromptChainer — A free and fast prompt chain generator

Productivity•Artificial Intelligence•Automation

LongCite — Generates fine-grained citations for large language models in long text question answering.

Programming•Long Text Question Answering•Citation Generation

LongLLaVA — Efficiently extending multimodal large language models to 1,000 images.

Image•Multimodal Learning•Image Processing

iText2KG — Incrementally build knowledge graphs using large language models.

Productivity•Knowledge Graph•Natural Language Processing

ChatMLX — A high-performance MacOS chat application based on large language models.

chatting•Chat•Large Language Models

EAGLE — Exploration of the design space for multimodal large language models

Programming•Multimodal Learning•Large Language Models

252

bonding_w_geimini — A Streamlit application utilizing the Gemini API for image object detection.

Image•Image Processing•Object Detection

parsera — A lightweight Python library for web scraping using large language models.

Programming•Python•Data Scraping

Data-Juicer — A one-stop data processing system that provides high-quality data for large language models.

Productivity•Machine Learning•Data Science

174

SpeechZap — An efficient speech-to-text recording tool.

Productivity•Speech to text•Real-time recording

ComfyUI-CogVideoXWrapper — A video processing tool that enables conversion from images to videos.

Video•Video Processing•Image to Video

186

MiniCPM-V 2.6 — High-performance multimodal language model suitable for image and video understanding.

Image•Multimodal•Image Understanding

162

MindSearch — An open-source AI search engine framework with performance comparable to Perplexity.ai Pro.

Programming•Search•Transformer

2094

SAM 2 — Next-generation real-time object segmentation model for video and images.

Image•Real-time object segmentation•Video processing

186

CLASI — High-quality, human-like simultaneous interpretation system.

Productivity•Simultaneous Interpretation•Multilingual

936

Meta-Llama-3.1-405B-Instruct-FP8 — Multilingual dialogue generation model

Programming•NLP•Multilingual

480

custom-pilot — Integrate custom code completion models into VS Code

Programming•Visual Studio Code•Code Completion

Picogen AI Image API — An AI image generation API providing high-quality 4K image generation and editing capabilities.

Image•AI Image Generation•4K Resolution

228

ICSFSurvey — A deep dive into the internal consistency and self-feedback of large language models.

Programming•Internal Consistency•Self-Feedback

DCLM — Comprehensive framework for building and training large language models

Programming•Large language models•Dataset construction

Best AI Websites & Tools