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
pydantic/pydantic-ai
PydanticAI is a Python agent framework designed to simplify the development of production-grade applications using Generative AI. It is created by the team behind Pydantic, a popular data validation and settings management library, and aims to bring the ergonomic and innovative design principles of FastAPI to AI-driven application development. PydanticAI supports multiple language models including OpenAI, Anthropic, Gemini, and others, providing a model-agnostic interface that allows developers to easily integrate various LLMs into their projects. The framework emphasizes type safety and structured responses by leveraging Pydantic's powerful validation capabilities, ensuring consistent and reliable outputs from AI models. It also integrates seamlessly with Pydantic Logfire for real-time debugging, performance monitoring, and behavior tracking, enhancing the development and maintenance experience of AI applications. PydanticAI offers a Python-centric design that uses familiar control flow and agent composition patterns, making it accessible to Python developers and enabling the application of standard best practices. The framework includes features such as dependency injection to supply data and services to system prompts, tools, and output validators, facilitating testing and iterative development. It supports streamed responses for continuous output validation and rapid feedback. Additionally, Pydantic Graph support allows for defining complex application flows using typing hints, helping to avoid convoluted control structures. The project provides clear documentation and examples, including a minimal 'Hello World' agent and a more advanced support agent example demonstrating tools and dependency injection. Overall, PydanticAI is a comprehensive and robust framework for building AI agents with strong typing, validation, and integration capabilities, aimed at making Generative AI application development more efficient and reliable.
https://github.com/pydantic/pydantic-ai
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.
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.
purocean/yn
Yank Note is a highly extensible Markdown editor featuring AI assistance, version control, encryption, code execution, and rich multimedia embedding for enhanced productivity.