AI & LLM SDKs Packages
SDKs and clients for large-language-model providers and inference, covering chat completions, embeddings, and streaming (OpenAI, Anthropic, Vercel AI).
Packages in AI & LLM SDKs
Kind
Sort:Used by Most Apps
async-openai
Async Rust client for the OpenAI API with builder-pattern requests, SSE streaming, and middleware support.
Laravel AI SDK
Unified, expressive API for interacting with AI providers from Laravel
Replicate Python Client
The official Python client for running machine learning models on Replicate
elevenlabs-js
The official Node.js SDK for the ElevenLabs voice AI API, covering text-to-speech, speech-to-text, dubbing, voice cloning, and real-time conversational agents in one typed client.
Qianfan Python SDK
The Python SDK for Baidu's Qianfan large-model (MaaS) platform, including ERNIE models.
langchain-nvidia-ai-endpoints
The official LangChain integration for NVIDIA-hosted chat, embedding, reranking, and retrieval models, deployable via the NVIDIA API Catalog or self-hosted NIM microservices.
DashScope
Official Python SDK for Alibaba Cloud's Model Studio (Bailian) generative AI APIs
langchain-litellm
The official LangChain integration that routes chat, embedding, and OCR calls through LiteLLM's 100+ provider unified API.
Portkey AI
Node.js SDK for Portkey's AI gateway, giving you one OpenAI-compatible client for any LLM provider with built-in retries, caching, and observability.
letta-node
The official TypeScript/JavaScript SDK for the Letta API, giving typed access to stateful agents, memory blocks, tools, and streaming responses.
dify-ai-provider
A Vercel AI SDK provider that turns any Dify.AI application into a drop-in language model.
langchain-ibm
The official LangChain integration for IBM watsonx.ai chat, embedding, rerank, and SQL agent models.
LangChain Unstructured
Official LangChain integration for loading and chunking documents with Unstructured
supermemory
Type-safe TypeScript SDK for the Supermemory memory API — add, search, and manage AI memories, documents, and connections.
Memori
LLM-agnostic memory infrastructure that turns agent conversations into persistent, structured, recallable state.
agents
A Python framework for building realtime, multimodal voice AI agents that can see, hear, and speak.
@openuidev/lang-core
The framework-agnostic parser, prompt generator, and runtime evaluator behind OpenUI Lang, the DSL that lets LLMs stream typed UI trees.
GitHub Copilot SDK (Rust)
Rust SDK for embedding GitHub Copilot's agentic workflows into your application over JSON-RPC.
baml
The Python runtime for BAML — a typed prompt language that compiles LLM calls into type-safe, testable client code.
OpenTelemetry Instrumentation for LanceDB
OpenTelemetry auto-instrumentation that traces client-side LanceDB calls in your Python GenAI and RAG applications.
OpenTelemetry Instrumentation for Marqo
OpenTelemetry auto-instrumentation that traces client-side Marqo calls in your Python GenAI and RAG applications.
OpenTelemetry Instrumentation for Milvus
OpenTelemetry auto-instrumentation that traces client-side Milvus calls in your Python GenAI and RAG applications.
OpenAI PHP
A community-maintained PHP API client for interacting with the full OpenAI API.
Llama Cloud Services
Python SDK for LlamaCloud's document parsing, extraction, and managed index services
