Ollama Workflows is an open-source library of configurable AI agent pipelines built on top of the Ollama LLM framework. It offers dozens of ready-made workflows—like summarization, translation, code review, data extraction, email drafting, and more—that can be chained together in YAML or JSON definitions. Users install Ollama, clone the repository, select or customize a workflow, and run it via CLI. All processing happens locally on your machine, preserving data privacy while allowing you to iterate quickly and maintain consistent output across projects.

Metaflow is a Python library that assists data scientists and engineers in building, managing, and scaling real-life data science projects. Originating at Netflix, Metaflow offers streamlined solutions for developing, deploying, and operating various data-intensive applications, particularly those involving machine learning (ML), artificial intelligence (AI), and data science. Offering coherent APIs, it simplifies workflow orchestration, data movement, version tracking, and scaling compute to the cloud, ensuring efficient project development from start to finish.

DALI provides a modular, extensible SDK for building document AI agents capable of ingesting images, PDFs, and scanned files. It integrates OCR engines and vision-language models to detect layout elements, extract tables, and answer user queries. Developers can customize pipelines, plug in different LLMs, and deploy interactive web or command-line interfaces. With built-in support for caching, batching, and multi-model orchestration, DALI accelerates document understanding tasks with minimal code.

Trinity-RFT (Retrieval Fine-Tuning) is a unified open-source framework designed to enhance model accuracy and efficiency by combining retrieval and fine-tuning workflows. Users can prepare a corpus, build a retrieval index, and plug the retrieved context directly into training loops. It supports multi-modal retrieval for text, images, and video, integrates with popular vector stores, and offers evaluation metrics and deployment scripts for rapid prototyping and production deployment.

Agent Control Plane offers a centralized control plane for designing, orchestrating, and operating autonomous AI agents at scale. Developers can configure agent behaviors via declarative definitions, integrate external services and APIs as tools, and chain multi-step workflows. It supports containerized deployments with Docker or Kubernetes, real-time monitoring, logging, and metrics through a web-based dashboard. The framework includes a CLI and RESTful API for automation, enabling seamless iteration, versioning, and rollback of agent configurations. With an extensible plugin architecture and built-in scalability, Agent Control Plane accelerates the end-to-end AI agent lifecycle, from local testing to enterprise-grade production environments.

ClassiCore-Public provides a comprehensive environment for building, optimizing, and deploying classification models. It features an intuitive pipeline builder that handles raw data ingestion, cleaning, and feature engineering. The built-in model zoo includes algorithms like Random Forests, SVMs, and deep learning architectures. Automated hyperparameter tuning uses Bayesian optimization to find optimal settings. Trained models can be deployed as RESTful APIs or microservices, with monitoring dashboards tracking performance metrics in real time. Extensible plugins let developers add custom preprocessing, visualization, or new deployment targets, making ClassiCore-Public ideal for industrial-scale classification tasks.