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
google/adk-java
The project "google/adk-java" is an open-source Java toolkit called the Agent Development Kit (ADK) designed for building, evaluating, and deploying sophisticated AI agents with a focus on flexibility and control. It targets developers who want fine-grained control over AI agent behavior and orchestration, especially those integrating with Google Cloud services. The toolkit allows defining agent logic, tools, and orchestration directly in Java code, which supports robust debugging, versioning, and deployment across various environments from local machines to cloud infrastructure. Key features include a rich ecosystem of tools that can be pre-built, custom, or integrated via OpenAPI specs, enabling diverse capabilities for AI agents tightly integrated with the Google ecosystem. The code-first development approach emphasizes flexibility, testability, and version control by allowing developers to write agent logic and tool usage directly in Java. The toolkit supports modular multi-agent systems, enabling scalable applications by composing multiple specialized agents into flexible hierarchies. The project provides a Maven dependency for easy installation and includes comprehensive documentation and sample projects to help developers get started. It offers a development UI similar to the Python ADK version, which facilitates testing, evaluation, debugging, and showcasing of agents. The project also plans to support agent evaluation features and integrates with the A2A protocol for remote agent-to-agent communication. The ADK for Java is licensed under the Apache 2.0 License and encourages community contributions including bug reports, feature requests, documentation improvements, and code contributions. It is positioned as a powerful toolkit for developers aiming to build advanced AI agents with tight integration into Google Cloud services, leveraging a code-first approach for maximum control and flexibility.
https://github.com/google/adk-java
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.