Agent Frameworks

Strands Agents is an open-source, model-driven framework for building AI agents with Python by combining an LLM, tools, and optional instructions into a lightweight agent loop.

AG2 is an open-source Python framework for building, orchestrating, and experimenting with multi-agent AI applications using conversational agents, tool use, human-in-the-loop workflows, and group chat coordination.

Haystack is an open-source Python framework by deepset for building production-ready LLM applications, retrieval-augmented generation systems, semantic search, question answering, and AI agents.

Pydantic AI is a Python framework from the Pydantic team for building type-safe, production-oriented AI agents using structured outputs, dependency injection, and model-agnostic LLM integrations.

Mastra is a TypeScript framework for building production-oriented AI agents, workflows, tools, memory, and RAG applications.

Semantic Kernel Agent Framework is Microsoft's agent orchestration layer within Semantic Kernel for building AI agents that use LLMs, tools, memory, plugins, and multi-agent collaboration across .NET, Python, and Java ecosystems.

LlamaIndex Workflows is an event-driven orchestration framework for building agentic, multi-step AI applications using composable async steps, events, and LlamaIndex components.

Google Agent Development Kit is an open-source, code-first framework for building, testing, evaluating, and deploying AI agents, especially agents powered by Gemini and Google Cloud services.

OpenAI Agents SDK is a lightweight Python framework for building, orchestrating, tracing, and evaluating AI agents that use OpenAI models, tools, handoffs, and guardrails.

Microsoft AutoGen is an open-source framework for building, orchestrating, and experimenting with multi-agent AI applications powered by LLMs, tools, humans, and event-driven workflows.

Agent orchestration capabilities within the LlamaIndex ecosystem for building data-aware AI applications with tool use, reasoning, and retrieval-augmented generation.

A multi-agent framework enabling role-based task delegation among specialized AI agents working together on complex workflows. It provides high-level abstractions for agent collaboration.

A framework by LangChain for building stateful, multi-actor applications with LLMs using graph-based agent orchestration. It supports cyclic graphs, human-in-the-loop, and persistent state.