LangChain
Open-source Python and TypeScript framework whose create_agent builds a configurable agent harness from a model, tools, a prompt and middleware.
Tags
Description
LangChain's docs position it between LangGraph (low-level orchestration) and Deep Agents (batteries-included harness); LangSmith handles tracing and evals. Python package langchain 1.4.7 on PyPI (MIT, Python >=3.10); JS/TS lives in langchain-ai/langchainjs (npm langchain 1.6.0, MIT). The docs publish an llms.txt and two remote docs MCP servers (see langchain-docs-mcp).
Agent access
Related
- LangGraph: Low-level orchestration framework from LangChain for building resilient, stateful agents as graphs.
- Deep Agents (LangChain): LangChain's batteries-included agent harness for agents that plan, spawn subagents and use a file system for complex tasks.
- LangSmith: LangChain's agent and LLM observability and evaluation platform: tracing, monitoring, cost and latency tracking.
- LangChain Docs MCP: Two free remote MCP servers from LangChain: one searches the LangChain, LangGraph and LangSmith docs, the other looks up API reference symbols.
Sources
- https://github.com/langchain-ai/langchain
- https://docs.langchain.com/oss/python/langchain/overview
- https://pypi.org/project/langchain/
- https://github.com/langchain-ai/langchainjs
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)