Back to directory

LangChain

A Python framework for building agents and LLM-powered applications from interoperable components, with a standard interface for models, embeddings, vector stores and integrations.

LangChain

LangChain is a framework for building LLM applications and agents. It chains together interoperable components and third-party integrations behind standard interfaces for chat models, embeddings, vector stores and retrievers, so models and providers can be swapped.

It is part of a wider ecosystem: Deep Agents for agents with planning, subagents and file system use; LangGraph for low-level agent orchestration; and LangSmith for evaluation, observability, debugging and deployment. A JavaScript and TypeScript version, LangChain.js, is also available.

LangChain installs as a Python package and is MIT licensed.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.