AI Frameworks
LLM application frameworks — LangChain, LlamaIndex, Haystack, DSPy.
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
A high-throughput and memory-efficient inference and serving engine for LLMs
Data framework for LLM applications — ingest, structure, and access private or domain-specific data via RAG and indexing.
Microsoft's lightweight SDK to integrate LLMs (OpenAI, Azure OpenAI, Hugging Face) with conventional programming languages — C#, Python, Java.
Framework for programming — rather than prompting — language models. Compiles LLM pipelines into self-improving, reproducible programs.
Production-ready LLM framework focused on RAG pipelines. Modular components for retrieval, generation and evaluation.
Stateful agents with long-term memory. OS-inspired hierarchical memory lets agents remember across sessions far beyond the context window.
Type-safe agent framework from the Pydantic team. Structured outputs, dependency injection, model-agnostic.