Breaker is an AI-native short video factory for content creators that automates the entire workflow from topic selection to performance review using a pipeline of five specialized agents.

Stars

112

7-day growth

No data

Forks

0

Open issues

0

License

No data

Last updated

2026-07-27

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It demonstrates a production-grade event-driven architecture with fail-closed design, minimal LLM usage (<15%), and a trust level system that progressively reduces manual oversight, backed by 577 test cases with zero network dependencies.

Who it is for

  • Content creators and influencers
  • Newcomers to short video creation
  • AI tool evaluators and reviewers
  • MCN operations teams

Use cases

  • Automate daily topic selection with a five-dimension scoring strategy report
  • One-click short video production with two rendering engines (Remotion template or ViMax original)
  • Weekly performance review with MAD attribution and plain-language suggestions
  • A/B test content elements (e.g., subtitle duration, BGM tempo) to improve engagement metrics

Strengths

  • EventBus-based agent architecture with correlation IDs for full traceability
  • Fail-closed seven-layer defense system ensures no silent failures
  • Only 15% of logic uses LLM, reducing cost and latency while improving reproducibility
  • 577 test cases with zero network dependencies (mocked external services), tests serve as specification

Considerations

  • MVP deployment on a 2-core 2GB server limits concurrent production to 3 items
  • Cold-start topic confidence is 0.6; requires account binding and 10 published videos to reach 0.9+
  • Trust level upgrade for ViMax (original) route takes 60 days due to diffusion uncertainty

README quick start

快速开始

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482