The full RAG + agent + eval stack for engineers building production LLM apps. PydanticAI for type-safe agents, Qdrant for vector memory, LangSmith for evals, OpenRouter for multi-model A/B testing, E2B for safe code execution. Designed to mirror what most LLM-app teams converge on after their first six months.
What's in this stack
- Claude CodeAnthropic's terminal-native coding agent with MCP-native tool use and skills system.npm_package
- AnthropicClaude model family — the default Claude Code provider. Sonnet, Opus, Haiku.env_key
- PydanticAIType-safe Python agent framework from the Pydantic team; MCP-native tool integration.pip_package
- QdrantRust-based OSS vector DB with payload filtering and hybrid search; self-host or cloud.mcp_docker
- LangSmithLangChain's hosted platform for tracing, eval, prompt versioning, and monitoring.pip_package
- OpenRouterSingle API key for 300+ models from every major provider, pay-per-use.env_key
- E2BSecure cloud sandboxes for AI-generated code — Python, Node, and full Linux environments.pip_package
How to use it
Click any entity above for its install instructions. Most are one-line installs; the MCP servers are JSON-config additions to your Claude Code config file.
The free Arcade tier lists these entities for browsing + per-entity install. Arcade Pro adds 1-click bulk-install: with one button in the desktop app, the entire stack lands configured and ready.