Build LLM application workflows with agents, chains, memory, and retrieval.
npx skills add https://github.com/ricable/mcai --skill langchain-ricable
Please help me install this Agent Skill. Skill: langchain Source: https://github.com/ricable/mcai/tree/main/.agents/skills/langchain Command: npx skills add https://github.com/ricable/mcai --skill langchain-ricable
This Skill helps you design, assemble, and deploy LLM-powered applications without stitching together scattered patterns and provider-specific code by hand. It reduces the friction of building chatbots, retrieval systems, tool-using agents, and conversational workflows that need to work reliably in real applications.
Use the langchain skill to build a tool-using LLM app or RAG pipeline for your chosen provider and data source.
High-intent search queries and answers about installing and using this skill.
You can build LLM apps with agents and RAG pipelines by assembling prompts, tools, and document retrievers. This approach supports chatbots, tool-using assistants, and retrieval-augmented generation across multiple model providers and vector stores.
The best way to add memory and persistence to a conversational LLM assistant is to integrate conversation history and persistent caches. This ensures longer-running assistant experiences maintain context and reliable behavior across multiple interactions.
Yes, you can swap model providers and vector stores in a RAG workflow with minimal refactoring. This integration flexibility allows you to change components like databases and deployment targets while maintaining your core retrieval and generation logic.
To create a tool-calling agent that reasons and calls external functions, you assemble ReAct agents within your LLM application. These agents can stream intermediate steps, call functions, and interact with external tools to deliver reliable production-ready behavior.
Components needed for a retrieval-augmented generation pipeline include document loaders, text splitters, embeddings, retrievers, and QA chains. Integrating these elements allows your LLM application to answer queries from internal documents effectively.
giuseppe-trisciuoglioBuild retrieval-augmented generation pipelines with vector databases and embedding models.
vellum-aiRename, list, export, and wipe Vellum assistant conversation threads via CLI.
t0dorakisDesign autonomous AI agents with tool use, memory, and multi-agent orchestration.
bobmatnycBuild and orchestrate LLM-powered applications with LangChain.
