Agent Frameworks & Orchestration

Agent Development Kit (ADK) is a framework for developers building AI agents and multi-agent workflows. It supports Python, TypeScript, Go, and Java, and is designed to run across different models and deployment setups.

AutoGen is a programming framework for building multi-agent AI applications. It’s aimed at developers who want agents that can use tools, browse the web, and work with humans in the loop.

Dify is a platform for creating AI apps, agents, chatflows, and workflows with either a cloud service or self-hosted setup. It offers a free sandbox and paid plans for individuals and teams that need higher usage, more workspaces, and collaboration.

Semantic Kernel is an open-source SDK for developers building AI agents and multi-agent workflows. It supports tool use, planning, memory, plugins, and local or cloud model backends.

ElizaOS is an open-source platform for building, deploying, and managing AI agents. It includes a CLI, web UI, and plugin-based architecture so you can run agents locally and extend them with integrations and custom logic.

MetaGPT assigns different roles to LLMs to simulate a software team. It can turn a short requirement into artifacts like user stories, requirements, APIs, and code repositories.

CrewAI AMP is a platform for building, testing, deploying, and managing agentic workflows. It targets teams that want visual tools and hosted or self-hosted deployment options for production AI agents.

Semantic Kernel is Microsoft’s lightweight, open-source framework for adding AI models and agent workflows to C#, Python, and Java applications. It helps developers connect prompts, plugins, memory, and model calls into software that can take actions through existing APIs.

LangChain is an open-source framework for building agents and LLM-powered applications. It helps developers connect models, tools, and external systems into multi-step workflows.

LlamaIndex helps developers build document agents that parse, extract, and reason over complex files. It combines agentic OCR with a low-code workflow builder for document-heavy automation.

Documentation for the Xet content-addressed storage protocol and its reference implementations. It is aimed at developers building clients or tools that upload and download data from Hugging Face Hub using Xet.

CAMEL-AI is an open-source community and Python framework for building multi-agent systems. It’s aimed at developers and researchers exploring agent behavior, data generation, world simulation, and task automation.

Coze is a no-code platform for creating chatbots and AI agents, then releasing them to web, APIs, and messaging platforms. It’s aimed at individuals, creators, and businesses that want to automate content, support, or workflow tasks without building from scratch.