Langchain Dependencies

Got sick of debugging LangChain dependency hell? This skill cuts through the ecosystem's package sprawl with current version requirements, compatibility matrices, and minimal working templates. It covers the core langchain/langsmith stack, provider integrations (OpenAI, Anthropic, etc.), and the LangGraph vs Deep Agents decision tree. The skill emphasizes LangChain 1.0+ for new projects and warns about langchain-community's non-semantic versioning gotchas. Includes ready-to-copy requirements.txt and package.json snippets for Python and TypeScript projects, plus environment minimums and tool package recommendations.

skills.sh installs: 16.8K
GitHub stars: 1.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add langchain-ai/langchain-skills --skill langchain-dependencies --agent claude-code

Installs into .claude/skills of the current project.

Files

The LangChain ecosystem is split into focused, independently-versioned packages. Understanding which packages you need — and their version constraints — prevents incompatibilities and keeps upgrades predictable.

Key principles:

LangChain 1.0 is the current LTS release. Always start new projects on 1.0+. LangChain 0.3 is legacy maintenance-only — do not use it for new work.
langchain-core is the shared foundation: always install it explicitly alongside any other package.
langchain-community (Python only) does NOT follow semantic versioning; pin it conservatively.
LangGraph vs Deep Agents: choose one orchestration approach based on your use case — they are alternatives, not a required stack (see Framework Choice below).
Provider integrations (model, vector store, tools) are installed separately so you only pull in what you use.