plugin CX Codex

llm-application-dev — Claude Code plugin: installation

Q: How do I install llm-application-dev in Claude Code?

Add the marketplace with `/plugin marketplace add wshobson/agents`, then install the plugin with `/plugin install llm-application-dev@claude-code-workflows`.

A plugin for building LLM apps, RAG systems, and LangGraph agents. Use it for vector search, embeddings, prompt work, and model evaluation.

Install into Claude Code · Plugin marketplace All methods and platforms ↓

/plugin marketplace add wshobson/agents
/plugin install llm-application-dev@claude-code-workflows

Open on GitHub

What llm-application-dev does

llm-application-dev provides skills and subagents for LLM application development. It covers production RAG with hybrid search, vector databases such as Pinecone, Qdrant, Weaviate, Milvus, and pgvector, plus LangGraph agents with memory and tool use.

The plugin includes ai-engineer, prompt-engineer, and vector-database-engineer, along with skills for LangGraph, LLM evaluation, embeddings, similarity search, and HNSW, IVF, and Product Quantization indexes. Its commands create an agent, build an AI assistant, and optimize prompts. The listed requirements are LangChain >= 1.2.0, LangGraph >= 0.3.0, and Python 3.11+.

The current patterns moved from LangChain 0.x to LangChain 1.x and LangGraph, so older code needs adaptation. Replacing initialize_agent() with LangGraph StateGraph workflows is one concrete change to account for.

What it helps with

create a LangGraph agent
build a RAG system with hybrid search
tune vector indexes and retrieval
choose an embedding strategy
evaluate and optimize prompts

Example prompts for the agent

Create a LangGraph agent with memory and tool use through /llm-application-dev:langchain-agent.
Build an AI assistant application with RAG and vector search using /llm-application-dev:ai-assistant.
Optimize the project prompts for production with /llm-application-dev:prompt-optimize.

How to install llm-application-dev

Plugin marketplace

/plugin marketplace add wshobson/agents

/plugin install llm-application-dev@claude-code-workflows

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about llm-application-dev

How do I install llm-application-dev in Claude Code?

Add the marketplace with /plugin marketplace add wshobson/agents, then install the plugin with /plugin install llm-application-dev@claude-code-workflows.

What does llm-application-dev do?

It supports LLM applications, RAG systems, vector search, and LangGraph agent architectures. The plugin also includes skills for prompt engineering, embeddings, and LLM evaluation.

What does the plugin require?

It requires LangChain >= 1.2.0, LangGraph >= 0.3.0, and Python 3.11+. Projects using LangChain 0.x need to move to LangChain 1.x and LangGraph patterns.

Source text

llm-application-dev · MIT

# LLM Application Development Plugin for Claude Code

Build production-ready LLM applications, advanced RAG systems, and intelligent agents with modern AI patterns.

## Version 2.0.0 Highlights

- **LangGraph Integration**: Updated from deprecated LangChain patterns to LangGraph StateGraph workflows
- **Modern Model Support**: Claude Opus 4.8/Sonnet 5/Haiku 4.5 and GPT-5.4/GPT-5-mini
- **Voyage AI Embeddings**: Recommended embedding models for Claude applications
- **Structured Outputs**: Pydantic-based structured output patterns

## Features

### Core Capabilities

- **RAG Systems**: Production retrieval-augmented generation with hybrid search
- **Vector Search**: Pinecone, Qdrant, Weaviate, Milvus, pgvector optimization
- **Agent Architectures**: LangGraph-based agents with memory and tool use
- **Prompt Engineering**: Advanced prompting techniques with model-specific optimization

### Key Technologies

- LangChain 1.x / LangGraph for agent workflows
- Voyage AI, OpenAI, and open-source embedding models
- HNSW, IVF, and Product Quantization index strategies
- Async patterns with checkpointers for durable execution

## Agents

| Agent                      | Description                                                                |
| -------------------------- | -------------------------------------------------------------------------- |
| `ai-engineer`              | Production-grade LLM applications, RAG systems, and agent architectures    |
| `prompt-engineer`          | Advanced prompting techniques, constitutional AI, and model optimization   |
| `vector-database-engineer` | Vector search implementation, embedding strategies, and semantic retrieval |

## Skills

| Skill                          | Description                                                 |
| ------------------------------ | ----------------------------------------------------------- |
| `langchain-architecture`       | LangGraph StateGraph patterns, memory, and tool integration |
| `rag-implementation`           | RAG systems with hybrid search and reranking                |
| `llm-evaluation`               | Evaluation frameworks for LLM applications                  |
| `prompt-engineering-patterns`  | Chain-of-thought, few-shot, and structured outputs          |
| `embedding-strategies`         | Embedding model selection and optimization                  |
| `similarity-search-patterns`   | Vector similarity search implementation                     |
| `vector-index-tuning`          | HNSW, IVF, and quantization optimization                    |
| `hybrid-search-implementation` | Vector + keyword search fusion                              |

## Commands

| Command                                | Description                     |
| -------------------------------------- | ------------------------------- |
| `/llm-application-dev:langchain-agent` | Create LangGraph-based agent    |
| `/llm-application-dev:ai-assistant`    | Build AI assistant application  |
| `/llm-application-dev:prompt-optimize` | Optimize prompts for production |

## Installation

```bash
/plugin install llm-application-dev
```

## Requirements

- LangChain >= 1.2.0
- LangGraph >= 0.3.0
- Python 3.11+

## Changelog

### 2.0.0 (January 2026)

- **Breaking**: Migrated from LangChain 0.x to LangChain 1.x/LangGraph
- **Breaking**: Updated model references to Claude 4.6 and GPT-5.4
- Added Voyage AI as primary embedding recommendation for Claude apps
- Added LangGraph StateGraph patterns replacing deprecated `initialize_agent()`
- Added structured outputs with Pydantic
- Added async patterns with checkpointers
- Fixed security issue: replaced unsafe code execution with AST-based safe math evaluation
- Updated hybrid search with modern Pinecone client API

### 1.2.2

- Minor bug fixes and documentation updates

## License

MIT License - See the plugin configuration for details.

Similar plugins

All plugins for AI and ML →

discernment-nudge official anthropics This plugin adds two or three short follow-up questions after a substantive answer. Use it to check facts, probe reasoning, and spot missing context. ★ 183,839repo stars academy-guide official anthropics Recommends Claude Academy courses, tutorials, and use cases when you ask how to use Claude. It suits people learning Claude features through real tasks. ★ 183,839repo stars claude-api official anthropics This plugin adds Claude API and SDK guidance for building LLM-powered applications. Install it when your project needs a Claude integration. ★ 183,839repo stars example-skills official anthropics A collection of Claude skill examples for web testing, MCP work, design and documents. Use it to inspect skill structure or start a custom skill from a template. ★ 183,839repo stars mem0 mem0ai Adds persistent memory to Claude Code so your agent retains project context across terminal sessions. ★ 67,829repo stars promptfoo-evals promptfoo Guides Claude Code in generating and maintaining promptfoo test suites for LLM apps. Covers hallucination checks, JSON schema validation, and CI setup. ★ 26,372repo stars

From the same set342

The whole set →