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
TanStack AI
Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps.
Weave
Open-source tracing, evaluation, and observability toolkit for building and debugging LLM-powered applications.
LlamaIndex
The leading data framework for building LLM applications over your own data.
CopilotKit
React hooks and providers for building AI copilots with shared state, generative UI, and human-in-the-loop workflows.
Opik
Python SDK for tracing, evaluating, and monitoring LLM applications, RAG pipelines, and agentic workflows.
Google Agent Development Kit (ADK)
An open-source, code-first Python framework for building and deploying AI agents
llama-cpp-python
Python bindings for llama.cpp to run local LLMs with an OpenAI-compatible API
ModelScope
Alibaba's open model-hub library for NLP, CV, speech, and multi-modal AI models.
OpenTelemetry Instrumentation for Anthropic
OpenTelemetry auto-instrumentation for the Anthropic Python SDK, tracing prompts and completions
Google Generative AI Python SDK
The original Python SDK for Google's Gemini API, now in maintenance-only mode and superseded by the unified Google Gen AI SDK.
AI Gateway Provider
Vercel AI SDK provider for Cloudflare AI Gateway with automatic fallback
Groq Python Library
The official Python client for the Groq LLM inference API
tiktoken-rs
Fast Rust library for tokenizing text and counting tokens for OpenAI GPT models with tiktoken BPE.
genai-prices
Calculate LLM API costs across 30+ providers with live, versioned pricing data
LangChain AWS
Official LangChain integrations for Amazon Bedrock, SageMaker, and other AWS services.
AssemblyAI Python SDK
Python SDK for AssemblyAI's speech-to-text and audio intelligence API, covering prerecorded, low-latency sync, and real-time streaming transcription.
Vertex AI SDK for Node.js
The official Node.js client for Vertex AI's Gemini models, now deprecated in favor of the Google Gen AI SDK.
Langfuse JS/TS SDK (@langfuse/client)
Universal JavaScript/TypeScript client for Langfuse: prompt management, dataset experiments, evaluation scores, and media uploads through one typed API.
typescript-sdk
The official TypeScript SDK for Voyage AI's embedding, reranking, and multimodal APIs, with built-in local on-device inference.
langchain-perplexity
LangChain integration package for Perplexity AI, providing chat models, embeddings, retrievers, and tools.
agno
Full-stack Python framework for building, running, and managing AI agent platforms
json-render
The Generative UI framework: AI builds real, reliable interfaces from prompts, constrained to components you define.
Chonkie
Lightweight, fast text-chunking library for RAG ingestion pipelines
Prism
A unified, fluent Laravel interface for working with large language models across every major AI provider.
