AI Frameworks
LangChain / LangGraph
Most popular LLM framework. 100K+ GitHub stars. Chains, RAG, vector stores, tool use. LangGraph adds stateful multi-agent workflows with cycles and persistence.
Try LangChain / LangGraphVisit langchain.comlangchain.com
Share
LangChain is the most popular framework for building LLM applications, with over 100K GitHub stars. It provides abstractions for chains (sequential LLM calls), RAG (retrieval-augmented generation with any vector store), tool use, and output parsing. LangGraph extends it with stateful, graph-based workflows - agents that can loop, branch, and persist state across interactions. A more recent addition is 'Deep Agents' for long-running autonomous tasks. LangSmith provides observability and tracing. The ecosystem is massive - integrations with every model provider, vector database, and tool imaginable. I cover LangChain in my AI Agent Frameworks course.
LangChain / LangGraph at a glance
Last verified
- Pricing
- LangChain and LangGraph libraries - free and open source (MIT)
- LangSmith Developer - $0/seat per month: 1 seat, up to 5k base traces/mo, then pay as you go
- LangSmith Plus - $39/seat per month: up to 10k base traces/mo, unlimited seats, 1 free small serverless deployment, then pay as you go
- LangSmith Enterprise - custom pricing, self-hosted and hybrid deployment, custom SSO, support SLA
- Usage beyond plan allowances is metered in LangChain Standard Units (1 LSU = $1)
- Install
pip install -U langchainpip install -U langgraphnpm install langchain @langchain/core- Models
- Model-agnostic: install a provider package (langchain-openai, langchain-anthropic, Google Gemini, AWS Bedrock, Azure, OpenRouter and many more) and pick a model with init_chat_model, for example init_chat_model("google_genai:gemini-3.7-flash"). New model names work without a LangChain update because provider packages pass them straight to the provider's API.
- Recent changes
- langgraph 1.2.16 (Python) and @langchain/langgraph 1.5.1 (JS) fix resume handling: other tasks finish when one resume value is invalid, and subgraphs no longer rerun finished tasks on resume.
- langchain 1.4.0 (Python) adds a langchain.mcp namespace with an MCPAdapter.
Sources: LangSmith pricing, Install LangChain (Python), Install LangChain (JavaScript), Install LangGraph, LangChain models, langchain 1.4.0 release, langgraph releases, langgraphjs releases
Similar Tools
AI Frameworks
Claude Agent SDK
Anthropic's SDK for building agents on the same tools, agent loop, and context management that power Claude Code. Python and TypeScript. Subagents, hooks, MCP, and permissions.
AI Frameworks
OpenAI Agents SDK
Python and TypeScript framework for multi-agent workflows. Agent handoffs, tool use, guardrails, sessions, tracing. Provider-agnostic, supporting the OpenAI Responses and Chat Completions APIs plus 100+ other LLMs.
AI Frameworks
CrewAI
Multi-agent orchestration framework. Define agents with roles, goals, and tools, then assign them tasks in a crew. Python-based. Great for complex workflows.
AI Frameworks
Mastra
TypeScript-first AI agent framework. Agents, tools, memory, workflows, RAG, evals, tracing, MCP, and production deployment for Node.js apps.
Get started with LangChain / LangGraph
Most popular LLM framework. 100K+ GitHub stars. Chains, RAG, vector stores, tool use. LangGraph adds stateful multi-agent workflows with cycles and persistence.
Try LangChain / LangGraphGet weekly tool reviews
Honest takes on AI dev tools, frameworks, and infrastructure - delivered to your inbox.
Subscribe FreeMore AI Frameworks Tools
Vercel AI SDK
The TypeScript toolkit for building AI apps. Unified API across OpenAI, Anthropic, Google. Streaming, tool calling, structured output, multi-step agents. 27K+ GitHub stars.
CopilotKit
Frontend stack for agent-native apps. React hooks, prebuilt copilot UI, AG-UI runtime, frontend tools, shared state, and human-in-the-loop flows.
Claude Agent SDK
Anthropic's SDK for building agents on the same tools, agent loop, and context management that power Claude Code. Python and TypeScript. Subagents, hooks, MCP, and permissions.
Related Guides
Guide
AI Agent Frameworks Compared: LangGraph vs CrewAI vs Mastra vs CopilotKit
Deep comparison of the top AI agent frameworks - LangGraph, CrewAI, Mastra, CopilotKit, AutoGen, and Claude Code.
AI AgentsGuide
Claude Code Setup Guide
Configure Claude Code for maximum productivity -- CLAUDE.md, sub-agents, MCP servers, and autonomous workflows.
AI AgentsGuide
MCP Servers Explained
What MCP servers are, how AI clients like Claude Code call their tools, how to add one through .mcp.json, and how to build your own in TypeScript.
AI AgentsRelated Posts
15 min read
AI Agents
LlamaIndex in 2026: Workflows, Agents, and What Changed
LlamaIndex in late 2026: Python Workflows 2.26 with typed events, human-in-the-loop and DBOS durability, plus LiteParse....
8 min read
AI
Buzz by Block: The Open-Source Workspace Where Humans and AI Agents Build Together
Buzz is Block's open-source Nostr relay workspace where humans and AI agents share rooms. Agent-first CLI, git as channe...
7 min read
RAG
Vector Database Comparison for RAG and AI Agents
pgvector, Pinecone, Qdrant, Weaviate, Chroma, Milvus, and Turbopuffer compared on hosting model, filtering, scale, and c...
7 min read
News
The Log Is the Agent: Event Sourcing Comes to AI Systems
Event sourcing for AI agents: a new paper makes the append-only log the source of truth for agent state. What it enables...
7 min read
AI
Agents 101: How to Build and Deploy Anything with AI Agents
Agents 101 companion guide: how to build and deploy AI agents fast on the Vercel agentic infrastructure stack, and where...
8 min read
AI Search
Agentic Search Works Best When It Writes Queries, Not Answers
SNEWPAPERS is a useful Show HN signal: the strongest agentic search products do not replace search results with prose. T...
Try the member tools free
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever