AI Agent Frameworks Packages
Frameworks for building LLM agents with tools, memory, and orchestration for multi-step, autonomous workflows (LangChain, LlamaIndex, CrewAI, LangGraph).
Packages in AI Agent Frameworks
MCP TypeScript SDK
The official TypeScript SDK for building Model Context Protocol servers and clients.
AI SDK
Provider-agnostic TypeScript toolkit for building AI apps and agents with any LLM.
Anthropic TypeScript SDK
The official TypeScript and JavaScript SDK for building on Anthropic's Claude API.
python-sdk
The official Python SDK for building Model Context Protocol servers and clients that expose tools, resources, and prompts to any LLM host.
LangChain.js
The TypeScript framework for building LLM-powered apps and AI agents from interoperable, swappable components.
LangChain
The most widely adopted Python framework for building LLM-powered agents and applications
LangGraph
A low-level orchestration framework for building stateful, multi-actor LLM agents as graphs
Daytona Python SDK
The official Python SDK for creating and managing secure Daytona AI code sandboxes
LangChain Community
Community-maintained third-party integrations for LangChain, covering chat models, vector stores, tools, and retrievers.
FastMCP
The fast, Pythonic framework for building Model Context Protocol servers, clients, and apps
MCP Go SDK
The official Go SDK for building Model Context Protocol servers and clients, maintained in collaboration with Google.
LangGraph
A low-level JavaScript/TypeScript framework for building stateful, controllable LLM agents as graphs, with durable execution and human-in-the-loop.
@e2b/code-interpreter
JavaScript/TypeScript SDK for running AI-generated code in stateful, isolated E2B cloud sandboxes
E2B
Python SDK for spinning up secure, isolated cloud sandboxes where AI agents can safely run code.
Pi
Self-extensible AI coding agent CLI with a terminal UI, tool calling, and session management
