Express Caption

Created by team AMD Express on July 12, 2026

Claude Code Anthropic Claude ChatGPT Gemini AI Gemma Generative Agents Opus Streamlit

Video Captioning

Express Caption is a video-captioning agent built for AMD Express Track 2. Upload a short clip (30 seconds to 2 minutes), and it will write a caption in four requested styles: formal (precise and objective), sarcastic (dry and deadpan), humorous_tech (developer in-jokes), and humorous_non_tech (warm, jargon-free wit). The scored deliverable is a headless Docker agent: it reads tasks from /input/tasks.json, streams each video straight from its URL via HTTP range requests (no full 4K download), and writes /output/results.json Built with Fireworks AI (Kimi K2.6 for vision and text), ffmpeg for frame and scene sampling, and faster-whisper for on-device speech transcription.

Category tags:

Web Application, Writing, Video, Summarization

Github Presentation Demo

Explore more applications

Thymus

Thymus is a lightweight hybrid token-efficient router designed to maximize accuracy while minimizing token costs in multi‑task LLM pipelines. It dynamically routes user queries across local and remote models on LLM providers.

The Disappointer

HuggingFace HubLLaMAAMD Developer Cloud

AI Classroom Edge Intelligence

A privacy-first classroom AI platform that routes sensitive work to local edge systems and eligible anonymized analysis to Fireworks AI, helping teachers make faster, safer instructional decisions even with unreliable internet.

AI Classroom Edge

AMD Developer CloudQwen3rest apiGithub CopilotCodexChatGPT

Taskly: Smart Multi-Model Task Router

Taskly classifies incoming tasks into 8 categories (QA, math, code, NLP) and routes each to the optimal Fireworks AI model with a tuned prompt — maximizing accuracy while minimizing token usage in a fully Dockerized pipeline.

RuntimeTerror

AMD Developer CloudAMD ROCm

router_007_v3

router_007_v2 is a Track 1 agent that records **zero billable tokens**: every answer is computed inside the container by a Qwen2.5-7B-Instruct model bundled in the Docker image and served in-process with llama-cpp-python

roc_auc_half

Claude CodeChatGPTAMD ROCmAMD Developer CloudCodexGemmaGPT-5NVIDIAQwen3

Lexyprep

Agent knows how to make thorough legal research based on my experience of winning legal cases. It understands your issue and advises on procedure

Lexyprep - Do you have a case

AMD Developer CloudAMD ROCmCodexGemma

Upcoming AI Hackathons
For Innovators & Creators

Explore more applications

Thymus

Thymus is a lightweight hybrid token-efficient router designed to maximize accuracy while minimizing token costs in multi‑task LLM pipelines. It dynamically routes user queries across local and remote models on LLM providers.

The Disappointer

HuggingFace HubLLaMAAMD Developer Cloud

AI Classroom Edge Intelligence

A privacy-first classroom AI platform that routes sensitive work to local edge systems and eligible anonymized analysis to Fireworks AI, helping teachers make faster, safer instructional decisions even with unreliable internet.

AI Classroom Edge

AMD Developer CloudQwen3rest apiGithub CopilotCodexChatGPT

Taskly: Smart Multi-Model Task Router

Taskly classifies incoming tasks into 8 categories (QA, math, code, NLP) and routes each to the optimal Fireworks AI model with a tuned prompt — maximizing accuracy while minimizing token usage in a fully Dockerized pipeline.

RuntimeTerror

AMD Developer CloudAMD ROCm

router_007_v3

router_007_v2 is a Track 1 agent that records **zero billable tokens**: every answer is computed inside the container by a Qwen2.5-7B-Instruct model bundled in the Docker image and served in-process with llama-cpp-python

roc_auc_half

Claude CodeChatGPTAMD ROCmAMD Developer CloudCodexGemmaGPT-5NVIDIAQwen3

Lexyprep

Agent knows how to make thorough legal research based on my experience of winning legal cases. It understands your issue and advises on procedure

Lexyprep - Do you have a case

AMD Developer CloudAMD ROCmCodexGemma