langchain-agents
LangChain provides a standard interface for building LLM agents that can use tools. Modern agent development is moving toward LangGraph to handle stateful, multi-turn, and non-linear logic that simple loops cannot capture.
npx skills add majiayu000/claude-skill-registry --skill langchain-agents --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
--- name: langchain-agents description: Building LLM agents with LangChain and LangGraph, covering tool-calling model initialization, state management, and observability with LangSmith. Triggers: langchain, langgraph, langsmith, agent-executor, chat-model-tools. --- # LangChain Agents ## Overview LangChain provides a standard interface for building LLM agents that can use tools. Modern agent development is moving toward LangGraph to handle stateful, multi-turn, and non-linear logic that simple loops cannot capture. ## When to Use - **Multi-Provider Apps**: When you want to swap between OpenAI, Anthropic, and local models without changing business logic. - **Stateful Agents**: When you need human-in-the-loop, long-term persistence, or complex execution graphs. - **Observability**: Using LangSmith to debug exactly where an agentic chain failed. ## Decision Tree 1. Is it a simple tool-calling loop? - YES: Use the `create_agent` abstraction. 2. Does it require cycles, complex state transitions, or human approval? - YES: Build using LangGraph. 3. Do you need to track exactly how much an agent run cost or where it halluncinated? - YES: Enable LangSmith tracing. ## Workflows ### 1. Creati
- Overview
- When to Use
- Decision Tree
- Workflows
- 1. Creating a Simple Tool-Enabled Agent
- 2. Debugging with LangSmith
- 3. Adding Memory to an Agent
- Non-Obvious Insights
- Evidence
- Scripts
- Dependencies
- References
What does the langchain-agents skill do?
LangChain provides a standard interface for building LLM agents that can use tools. Modern agent development is moving toward LangGraph to handle stateful, multi-turn, and non-linear logic that simple loops cannot capture.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill langchain-agents --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.