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
helixml/helix
HelixML is a private Generative AI (GenAI) stack designed to enable the building and deployment of AI applications with a focus on data security, control, and scalability. It offers a declarative pipeline approach, allowing users to create AI workflows using a simple configuration file (helix.yaml). The platform supports Retrieval-Augmented Generation (RAG), API bindings, and fine-tuning of models, making it versatile for various AI use cases including language and image models. HelixML can be deployed privately in data centers or virtual private clouds (VPCs), ensuring that sensitive data remains secure and under the user's control. The system optimizes the balance between GPU memory usage and latency, providing efficient performance for AI workloads. Installation options include a quickstart Docker installer and Helm charts for Kubernetes, catering to different deployment preferences. The platform supports attaching GPU runners and can integrate with any OpenAI-compatible large language model (LLM) API, enhancing flexibility. HelixML is also designed with developer convenience in mind, offering local development guides and comprehensive documentation. The project is licensed under terms similar to Docker Desktop, allowing free use for personal, educational, and small business purposes, while restricting commercial use and competition with the company. This licensing approach supports the sustainability of the project by preventing cloud providers from rebranding and monetizing the open-source code without contributing back. Overall, HelixML provides a robust, scalable, and secure environment for organizations and developers to leverage open-source AI technologies in a private setting, with features that simplify AI application development and deployment.
https://github.com/helixml/helix
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.