AI Frameworks

The most widely used framework for composing LLM applications, with hundreds of integrations for models, vector stores and tools.

Microsoft's framework for building multi-agent conversational systems with an event-driven, asynchronous architecture.

A data framework for connecting custom data sources to LLMs, specialising in retrieval-augmented generation.

A high-throughput, memory-efficient inference and serving engine for LLMs, widely used for self-hosting open models.

A framework for orchestrating role-playing autonomous AI agents that collaborate as a crew to complete tasks.

Microsoft's enterprise SDK for integrating LLMs into applications with plugins, planners and memory.

A framework from Stanford for programming — not prompting — language models, with automatic prompt and weight optimization.

An open-source framework by deepset for building production-ready RAG and search pipelines with LLMs.

A low-level orchestration framework for building stateful, multi-actor agent applications with cycles and checkpointing.

An agent framework from the Pydantic team bringing type-safe, structured outputs and validation to LLM applications.