Agentic Engineering Toolkit

Available

MCP servers, skills, and RAG pipelines for AI-accelerated development

A suite of production-tested tools that let AI agents operate autonomously across codebases: MCP servers for domain knowledge, structured skill systems, and multi-codebase RAG with pgvector.

This toolkit is what I use every day to build software faster. It includes MCP servers in Python and Java that serve multi-codebase domain knowledge via RAG with pgvector embeddings. Structured skill and context file architectures (CLAUDE.md, SKILL.md, AGENT.md) define boundaries and capabilities for autonomous coding agents.

The impact is measurable: at BluePallet, non-trivial feature development dropped from approximately 4 weeks to 2 weeks on production codebases. Code review turnaround went from days to under 15 minutes.

Also includes multi-agent delegation patterns for parallel work across isolated project workspaces, and an internal AI support agent for production triage and diagnostics.

Key Features

  • MCP servers in Python and Java serving multi-codebase domain knowledge
  • Structured skill/context file systems for autonomous agent operation
  • Prompt architectures for feature implementation, code review, and automation
  • Multi-agent delegation patterns for parallel work across projects
  • Internal AI support agent for production triage and diagnostics
  • RAG pipeline with pgvector embeddings for code and documentation

Built With

PythonJavaClaude CodeMCPpgvectorRAG

Interested in this solution?

I can help you deploy, customize, or build something similar for your specific needs.