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
LlamaParse
GenAI-native document parser that turns complex files into LLM-ready text and Markdown.
AI Elements
A CLI and shadcn/ui-based component registry for building AI-native chat interfaces on top of the Vercel AI SDK.
LangChain Rust
Build LLM-powered applications in Rust with composable chains, agents, tools, and vector stores.
OpenInference Core
Shared OpenTelemetry tracing foundation for instrumenting LLM applications with OpenInference semantic conventions
llama-cpp-2
Safe, up-to-date Rust bindings to llama.cpp for local LLM inference
deepgram-python-sdk
Official Python SDK for Deepgram's speech-to-text, text-to-speech, and voice agent APIs, with sync, async, and WebSocket support.
toolbox-core
Google's framework-agnostic Python SDK for loading and invoking MCP Toolbox database tools as native async functions.
OpenAI Dive
An unofficial async Rust SDK covering nearly every OpenAI API endpoint, from chat completions to realtime WebSocket streaming.
arcade-js
Official TypeScript/JavaScript client for the Arcade API, giving agents typed access to tool execution, authorization, and chat completions.
@sanity/assist
AI-powered writing, translation, and image-description assistant for Sanity Studio
together
The official Python SDK for the Together AI REST API, with typed sync and async clients.
Supermemory Python SDK
Official Python client for the Supermemory memory API, with typed sync and async access to memory, search, and document endpoints.
Braintrust Python SDK
Official Python SDK for logging, tracing, and evaluating AI applications with Braintrust
