World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.
Repository Index
47,133 repositories indexed
1–24 of 24 · Most stars
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Making large AI models cheaper, faster and more accessible
- deep-learning
- hpc
- large-scale
- data-parallelism
☁️ Build multimodal AI applications with cloud-native stack
- neural-search
- cloud-native
- deep-learning
- machine-learning
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
- pytorch
- speech-recognition
- paraformer
- punctuation
Unified framework for building enterprise RAG pipelines with small, specialized models
- parsing
- retrieval-augmented-generation
- agents
- generative-ai-tools
Always know what to expect from your data.
- pipeline-tests
- dataquality
- datacleaning
- datacleaner
Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable, and modular.
- kedro
- hacktoberfest
- mlops
- python
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
- bloom
- deep-learning
- distributed-systems
- language-models
ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.
- mlops
- machine-learning
- data-science
- production-ready
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
Elyra extends JupyterLab with an AI centric approach.
- notebooks
- notebook-jupyter
- jupyterlab
- jupyterlab-extensions
A full spaCy pipeline and models for scientific/biomedical documents.
- scientific-documents
- spacy
- custom-pipes
- nlp
A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
- healthcare
- data-mining
- deep-learning
- preprocessing
Python Streaming DataFrames for Kafka
MLBox is a powerful Automated Machine Learning python library.
- machine-learning
- auto-ml
- kaggle
- deep-learning
Extra blocks for scikit-learn pipelines.
- scikit-learn
- machine-learning
- common-sense
Pythonic tool for orchestrating machine-learning/high performance/quantum-computing workflows in heterogeneous compute environments.
- hpc
- workflow
- workflow-automation
- workflow-management
The world's cleanest AutoML library ✨ - Do hyperparameter tuning with the right pipeline abstractions to write clean deep learning production pipelines. Let your pipeline steps have hyperparameter spaces. Design steps in your pipeline like components. Compatible with Scikit-Learn, TensorFlow, and most other libraries, frameworks and MLOps environments.
- pipeline
- pipeline-framework
- machine-learning
- deep-learning
BatchFlow helps you conveniently work with random or sequential batches of your data and define data processing and machine learning workflows even for datasets that do not fit into memory.
- python3
- data-science
- machine-learning
- python
On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.
A Macau food recommendation Agent built on Thompson Sampling + StackedPareto weight fusion, with a full evaluation pipeline (5-fold CV, bootstrap CIs, stress tests) on 5,000 simulated users and 100k interactions. Competition entry for the QwenPaw AI Developer Challenge.
Build and deploy a serverless data pipeline on AWS with no effort.
- aws-cdk
- data-pipeline
- stepfunctions
- glue
A Multilingual Latent Dirichlet Allocation (LDA) Pipeline with Stop Words Removal, n-gram features, and Inverse Stemming, in Python.
- lda
- multilingual
- machine-learning
- latent-dirichlet-allocation