🦜🕸️ Awesome LangGraph & LangChain Ecosystem

The definitive index of frameworks, templates, and real-world projects for teams that want to build, observe, evaluate, and deploy stateful, tool-using AI agents with the LangChain + LangGraph stack.

Whether you’re prototyping your first workflow or operating production systems, this list maps the full lifecycle of agent development, from building with core libraries and integrations, to observing runs with platform tooling, evaluating quality and behavior, and deploying reliable agent applications.

What you’ll find - Core frameworks: LangChain, LangGraph, Deep Agents, and LangSmith - Resources for building, observing, evaluating, and deploying agent systems - Integrations & MCP tooling across models, vector stores, loaders, and tools - Official LangChain/LangGraph projects and prebuilt agent libraries - Community projects grouped by use case (RAG, web automation, research, finance, etc.) - Starter templates and learning resources to get productive fast

Contributions welcome—see the Contributing Guide.

---

Table of Contents

• 🦜🕸️ Awesome LangGraph \& LangChain Ecosystem
• Table of Contents
• Ecosystem Components:
  • LangChain 🔗
  • LangGraph 🕸️
  • Deep Agents 🧠
  • LangSmith 🛠️
  • LangSmith Fleet 🧩
  • LangChain Integrations \& Partners 🤝
• Official Libs, Apps and Tools 🟢
• 🌟 Community Projects
• 🧬 Bio \& Health
• 🌐 Web Automation \& Scraping
• 📊 Business Intelligence \& Market Research
• 🖥️ Chat Interfaces \& GUIs
• ☁️ Cloud \& DevOps
• 🤖 Coding/Dev Agents
• 🛎️ Customer Ops
• 📊 Data Platforms
• 🧮 Data Science
• 🛠️ Developer Tools
• 📦 Packages
• 💰 Finance \& Fintech
• 🎯 Marketing
• 🎥 Media \& Podcasts
• 🤖 Robotics \& Embodied AI
• 📚 RAG \& Document Processing
• 🔬 Research Agents
• 🛠️ Cybersecurity
• 🌍 Sustainability
• 📋 Templates \& Starters
• 🏢 Workplace \& Productivity
• 📚 Learning Resources
• 📖 Additional Resources
• 👥 Communities
• 🤝 Contributing
• 🙏 Acknowledgments

---

🌐 What is the LangChain/Graph Ecosystem

The LangChain/Graph Ecosystem is a comprehensive suite of frameworks and platforms for building, deploying, and managing LLM-powered applications. While LangGraph can be used standalone, it integrates seamlessly with any LangChain product, giving developers a full suite of tools for building agents.

_{Source: LangChain Documentation}

Ecosystem Components:

🔗 LangChain - Provides integrations and composable components to streamline LLM application development. Contains agent abstractions built on top of LangGraph.

🕸️ LangGraph - The core framework for building stateful, multi-agent systems with complex workflows, collaboration, and memory management.

🧠 Deep Agents - An agent harness for building agents that can plan, decompose complex tasks, use subagents, manage large context with filesystem tools, and persist long-term memory.

🛠️ LangSmith - The platform layer for observing, evaluating, and deploying AI agents and LLM applications with tracing, prompt engineering, Agent Server deployment, sandboxes, and operational tooling.

🧩 LangSmith Fleet - A no-code platform for creating and managing AI agents from templates, connecting apps and accounts, automating routine work, and keeping humans in control with approvals and oversight.

🤝 LangChain Integrations & Partners - Third-party integrations and provider packages that extend LangChain's capabilities across the AI ecosystem. These integration packages provide standardized interfaces to work with popular AI services, databases, and tools.

---

🦜 LangChain 🔗

LangChain is the foundational framework for building applications with Large Language Models (LLMs). It provides standardized interfaces, reusable components, and extensive integrations that enable developers to create sophisticated AI applications through composable building blocks.

▫️ Core Components and Usage ▫️

Essential building blocks and advanced capabilities for LangChain applications - from fundamental components to sophisticated AI features.

Core Components

Essential building blocks for LangChain applications

Component	Description
🤖 Agents	Decision-making systems that use LLMs to determine which actions to take
🧠 Models	Unified interfaces for LLMs and embedding models across providers
💬 Messages	Structured communication format between components
🛠️ Tools	External function calls and integrations for agents
🧭 Short-term Memory	Working memory for maintaining conversation context
⚡ Streaming	Real-time response processing for partial results

Advanced Usage

Advanced capabilities and techniques for sophisticated AI applications

Feature	Description
🧠 Long-term Memory	Persistent memory that survives across sessions
🛡️ Guardrails	Safety checks and policy enforcement for agent inputs, outputs, and tool usage
🎯 Context Engineering	Techniques for optimizing prompts and context management
📋 Structured Output	Generate responses in specific formats and schemas
🔗 Model Context Protocol	Standardized tool integration and context sharing
👥 Human-in-the-Loop	Approval workflows and interrupt-based human oversight for sensitive agent actions
🤝 Multi-agent	Coordinated systems with multiple AI agents
🔍 Retrieval	Advanced document retrieval and RAG patterns
⚙️ Runtime	Production deployment and runtime management
🔧 Middleware	Custom processing layers and request/response modification

▫️ LangChain Libraries ▫️

Package	Python	TypeScript	Description
LangChain	langchain	langchain	Main framework with chains, agents, retrieval methods, and cognitive architecture
LangChain Core	langchain-core	@langchain/core	Base abstractions and runtime for the entire ecosystem
Community	langchain-community	@langchain/community	Third-party integrations and community contributions
MCP Adapters	langchain-mcp-adapters	-	Make Anthropic MCP tools compatible with agents
Text Splitters	langchain-text-splitters	@langchain/textsplitters	Document processing and text splitting utilities
Experimental	langchain-experimental	@langchain/experimental	Beta features and experimental components
CLI Tools	langchain-cli	-	Command line interface for project management
Legacy	langchain-legacy	-	Legacy components from pre-v1.0 (Python only)

▫️ LangChain Documentation ▫️

Access the official LangChain documentation across the current unified docs experience and legacy redirect URLs:

Docs	Python	JavaScript	Notes
Current Open Source Docs	Overview	Overview	Current unified LangChain OSS docs on docs.langchain.com
Legacy Redirects	Legacy Entry	Legacy Entry	Older URLs that now redirect to the current overview docs

AI-accessible documentation format for LLMs and IDEs - LangChain now exposes a unified llms.txt entrypoint on docs.langchain.com for programmatic access to the latest documentation across LangChain, LangGraph, LangSmith, and API references.

Available Files

Scope	llms.txt	llms-full.txt
Unified LangChain Docs	docs.langchain.com/llms.txt	N/A
Legacy Redirects	python.langchain.com/llms.txt, js.langchain.com/llms.txt	N/A

Format Differences

• llms.txt - Unified index file with links and summaries for the latest LangChain ecosystem docs
• Legacy llms.txt URLs - Older Python and JavaScript endpoints that currently redirect to the unified docs file

⚠️ Review Output: Even with up-to-date documentation, current models may not always generate correct code. Always review generated code before production use.

---

🦜 LangGraph 🕸️

LangGraph is an open-source framework for building AI agents and multi-agent systems as graphs, and is a core part of the LangChain Ecosystem. It focuses on agent orchestration, enabling sophisticated AI applications that can maintain state, coordinate multiple agents, and handle complex reasoning processes through graph-based workflows.

▫️ Core Features ▫️

Capability	Description	Key Features
💾 Persistence	State persistence across executions and failures	Checkpointing, state recovery, session continuity
🔄 Durable Execution	Build agents that persist through failures and run for extended periods	Automatic resume, failure recovery, long-running workflows
⚡ Streaming	Real-time execution with partial results and live updates	Token streaming, progress tracking, responsive UX
⏸️ Interrupts	Pause graph execution for human input, review, and intervention	Approval checkpoints, state editing, resumable workflows
⏰ Time Travel	Navigate through agent execution history and states	State debugging, execution replay, historical analysis
🧠 Add and Manage Memory	Comprehensive memory management for stateful agents	Short-term working memory, long-term persistence, memory optimization
📊 Subgraphs	Nested graph structures for complex workflow composition	Modular workflows, reusable components, hierarchical execution
🧪 Testing	Validate graph behavior with unit and partial-execution testing patterns	Node testing, partial execution, checkpointer-based test setup
**👀 [Observability](https://docs.langchain.com/oss/python/langgraph