Browse by runtime
Find examples filtered to your specific library or agent framework.
Supported runtimes
Examples are tagged by the library or framework they demonstrate: LangChain, LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, and framework-agnostic patterns. Framework-agnostic examples apply to any runtime and are the most portable — start with these if you are evaluating options.
How to filter
Use search_examples(library="langchain", limit=10) via MCP to retrieve examples for a specific runtime during a session. On the examples page, use the runtime filter in the sidebar. Framework-agnostic examples are always shown regardless of the active filter.
What runtime coverage means
Runtime coverage means the example has been validated against that library. It does not mean the principle only applies to that library — all Blueprint principles apply across runtimes. Runtime filtering helps you see what a pattern looks like in your specific stack, not which principles are relevant to you.
OpenAI SDK61
Intelligence: The "brain" that processes information and makes decisions using LLMs.
This component handles context understanding, instruction following, and response generation.
Memory: Stores and retrieves relevant information across interactions.
This component maintains conversation history and context to enable coherent multi-turn interactions.
Tools: Enables agents to execute specific actions in external systems.
This component provides the capability to make API calls, database updates, file operations, and other practical actions.
Validation: Ensures LLM outputs match predefined data schemas.
This component provides schema validation and structured data parsing to guarantee consistent data formats for downstream code.
Pydantic12
Level 1: Augmented LLM — Single API Call
One model call with structured output, system prompt, and context. No loops, no tools.
Level 2: Prompt Chains & Routing — Deterministic DAGs
Multiple LLM calls in a fixed sequence. Code controls the flow, not the model.
Level 3: Tool-Calling Agent — Scoped Autonomy
The agent decides which tools to call and in what order, but only within a fixed set of well-defined capabilities.
Level 4: Agent Harness — Full Runtime Access
Give the agent a full runtime via the agent runtime SDK. It can search files, read docs, and reason through problems autonomously.
MCP8
Client Sse
Runnable example (advanced) for script using mcp.
Client Stdio
Runnable example (advanced) for script using mcp.
Client Streamable Http
Runnable example (advanced) for script using mcp.
Server
Runnable example (advanced) for script using mcp, python-dotenv.
Streamlit1
Docling1
Mem01
Other libraries12
Also in this section