What is LangChain?
Latest launch MIT
Summary
LangChain is an open-source agent engineering platform and Python framework for building agents.
- Category
- Frameworks
- Open source
- Yes
- License
- MIT
- Pricing
- Not stated in the sources on this page.
LangChain is described by its GitHub repository as "The agent engineering platform." The docs overview shows a create_agent function that takes a model, tools and a system prompt, with provider packages such as OpenAI, Anthropic and Ollama.
This hub was created with the dated launch langchain-anthropic 1.7.6, released October 12, 2026. Browse more in the frameworks category.
LangChain alternatives
| Tool | License | Pricing note |
|---|---|---|
LangChainThis pageLangChain is an open-source agent engineering platform and Python framework for building agents. | MIT | Not stated |
LangGraphLangGraph is an open-source orchestration runtime for building stateful, resilient agents. | MIT | Not stated |
CrewAICrewAI is a framework for orchestrating role-playing, autonomous AI agents that work together. | MIT | Not stated |
Pydantic AIPydantic AI is a model-agnostic Python framework for building typed AI agents and applications. | MIT | Not stated |
MastraTypeScript agent framework. Mastra Code is the terminal agent; AgentController is the extracted loop, in @mastra/core 1.47.0 or later. | Open source | Mastra Code and AgentController are announced as open source. No license fee is stated in the posts we cited. |
Launches and updates
langchain-anthropic 1.7.6 declares mid-conversation support
LangChainlangchain-anthropic 1.7.6, released October 12, 2026, declares mid-conversation support in model profiles and bumps langgraph-sdk and urllib3.
Category: Frameworks
Pricing: Open source
Guides covering LangChain
Questions
What is langchain?
The GitHub repository describes langchain as "The agent engineering platform."
Is langchain open source?
The GitHub API reports an MIT license for langchain-ai/langchain.
How do I create an agent with langchain?
The docs overview shows importing create_agent from langchain.agents and passing a model, tools and a system prompt.