Architectural Blueprint: This kit is currently a planned architectural blueprint. The specifications, threat model, and rules below describe the planned implementation. Starter source containers and automated test suites are in active development.
Blueprint Specification v1.0.0-blueprint

Production RAG Stack (Blueprint)

Production Retrieval-Augmented Generation. Ingest, chunk, embed, retrieve, generate with tenant isolation and eval benchmarks.

Python 3.12+ FastAPI Qdrant / Chroma LangChain LlamaIndex Ollama OpenAI
Agent Bootstrapping

Pre-Wired Rules

Single-source rules compiled to 6 native agent dialects. Transpiled deterministically from rules/source/.

• .cursor/rules/*.mdc
• CLAUDE.md
• .agents/rules/*.md
• .clinerules & CODEX.md
Security Guardrails

Automated Scanners

Invariants asserted in CI before merge. Scanned by Gitleaks and Semgrep AST checkers.

  • ✓ Planned: Gitleaks Secret Scanning Pre-configured
  • ✓ Planned: Semgrep Static Analysis Ruleset Active
  • ✓ Planned: Mandatory Authorization & RBAC on All Resources
Docker Scaffolding

Turnkey Containers

Runnable containers with pre-wired environment variables, healthchecks, and dependency locks.

docker compose up -d

Agent Bootstrap Prompt

Feed this exact prompt into Claude Code, Cursor, Copilot, or Antigravity to anchor the agent:

You are building with the Production RAG Stack kit. Follow rules in AGENTS.md, DESIGN.md tokens, and steps/agent-build-steps.md.