langgenius/dify
Dify is an open-source platform for developing and deploying AI applications using large language models, featuring workflow building, model management, agent capabilities, and observability tools.
Awesome AI Agents › AI Application Development
zenml-io/zenml
ZenML is an advanced AI platform designed to streamline the development, deployment, and management of machine learning (ML) and artificial intelligence (AI) workflows. It caters to ML and AI engineers working on traditional ML use cases, large language model (LLM) workflows, and agent-based systems within enterprise environments. The core functionality of ZenML revolves around enabling users to write workflows or pipelines that can run seamlessly on any infrastructure backend, referred to as stacks. This flexibility allows embedding any Pythonic logic within these pipelines, such as model training or running agentic loops. ZenML operationalizes AI applications by automatically containerizing and tracking code, monitoring individual runs with metrics, logs, and metadata, and abstracting infrastructure complexities. It integrates with existing tools and platforms like MLflow, Langgraph, Langfuse, AWS Sagemaker, and Google Cloud Platform Vertex AI, facilitating smooth interoperability. The platform supports rapid experimentation and iteration through an observable layer that works both in development and production environments. The architecture of ZenML is based on a client-server model with an integrated web dashboard for monitoring and management. It supports local development by running both client and server locally and production deployment by separating the server and connecting clients remotely. ZenML is widely adopted by numerous companies, including Airbus, AXA, JetBrains, Rivian, and others, highlighting its robustness and enterprise readiness. ZenML offers comprehensive documentation, tutorials, and examples to help users get started quickly, including guides for building AI pipelines, deploying ML models, managing LLM operations, and orchestrating agentic workflows. It also features a unique MCP Server that allows users to interact with their ML pipelines using natural language queries, enhancing usability and accessibility. Overall, ZenML is a powerful, flexible, and user-friendly platform that simplifies the complexities of AI workflow management, making it an essential tool for organizations aiming to operationalize AI at scale.
https://github.com/zenml-io/zenml
Also in AI Application Development
daytonaio/daytona
Daytona is a secure and elastic infrastructure platform designed for safely running AI-generated code with high performance and scalability.
e2b-dev/awesome-ai-agents
A curated and comprehensive list of AI autonomous agents categorized into open-source and closed-source projects, serving as a valuable resource for exploring, building, and contributing to AI agent development.
mlflow/mlflow
MLflow is an open-source platform that manages the full machine learning lifecycle, providing tools for experiment tracking, model packaging, deployment, evaluation, and observability in one integrated solution.
pydantic/pydantic-ai
PydanticAI is a Python agent framework that simplifies building production-grade Generative AI applications by providing type-safe, structured, and model-agnostic integration with multiple LLMs, along with features like dependency injection and real-time debugging.
GoogleCloudPlatform/generative-ai
A comprehensive repository of sample code, notebooks, and resources for developing and managing generative AI workflows on Google Cloud using Gemini models on Vertex AI.
0xPlaygrounds/rig
Rig is a Rust library for building scalable, modular, and ergonomic fullstack agents powered by large language models, supporting multiple LLM providers and vector stores for AI integration.
mnfst/manifest
Manifest is an open-source components library built on shadcn/ui for creating customizable and production-ready UI components to develop ChatGPT and conversational AI applications efficiently.