By laurigates
Build and orchestrate LangChain/LangGraph AI agents in TypeScript and Python with stateful graphs, subagent delegation, persistent memory, human-in-the-loop workflows, and project scaffolding for rapid development.
Build hierarchical AI agents using the deep-agents TypeScript/npm package. Use when you want to create an orchestrator agent that plans and executes multi-step tasks, manages file system context, delegates subtasks to child agents, or maintains persistent memory across runs with the Deep Agents library.
LangChain JS/TS framework for building LLM-powered applications - models, chains, tools, and RAG patterns.
Initialize a new LangChain TypeScript project with recommended configuration
Build stateful AI agents in Python using LangGraph's graph-based workflow framework. Use when you want to create a state machine agent with checkpoints, define agent behavior as a graph of nodes and edges, add human-in-the-loop approval steps, or compose multiple agents as subgraphs in a LangGraph application.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub laurigates/claude-plugins --plugin langchain-pluginGit workflows - commits, branches, PRs, issue processing, auto-close detection, and repository management
Claude Code hooks for enforcing best practices and workflow automation
General utilities - fd, rg, jq, yq, nushell, shell, imagemagick, mermaid, d2
ComfyUI custom-node pack lifecycle - scaffold a pack, create + seed the repo, open the gitops adoption PR, publish to the Comfy Registry, and add README screenshots
Project infrastructure standards - comprehensive project configuration for pre-commit, CI/CD, Docker, testing, linting, formatting, and more
Battle-tested Claude Code plugin for engineering teams — 38 agents, 156 skills, 72 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Language-agnostic development process harness implementing the Stateless Agent Methodology (SAM) 7-stage pipeline with ARL human touchpoint model and Voltron-style language plugin composition. Provides orchestration, workflows, planning, verification, and testing methodology that any language plugin can compose with.
Prompt engineering techniques for accurate, grounded Claude responses — anti-hallucination workflow with citation-backed analysis
Multi-agent orchestration system with MCP tools and Claude Code plugin agents. 51 specialized agents for development workflows, code quality, deployment, research, and more.
AI-powered development tools. 19 agents, 22 commands, 30 skills, 1 hook, 1 MCP server for code review, research, design, and workflow automation.
Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.