screwdriver-wrenchHands on Examples

Use these examples after Quick Startarrow-up-right to explore real scenarios with runnable code and CLI commands.

circle-check
circle-info

Audience: Engineers prototyping orchestration, PMs preparing demos, and data developers running evaluations without coding.

circle-info

TUI Development: Many examples below demonstrate Textual-based TUI patterns. For comprehensive TUI guidance, refer to the TUI foundation spec in the repository.

circle-info

Note: Validated example projects are now centralized in the GL SDK Cookbookarrow-up-right. This ensures all blueprints remain self-contained, runnable, and maintained with the latest SDK best practices.

Each row links to a runnable project. Follow the README for quick start instructions, then inspect code to understand the pattern.

Validated Example Projects

These projects demonstrate foundational patterns and are maintained in the GL SDK Cookbookarrow-up-right. Each project is self-contained and ready to run.

Pattern
Description
Project Link

Basic Agent (Hello World)

A minimal starter demonstrating how to create and run an agent using config-based instantiation.

Modular Tool Integration

Learn how to organize complex tools with separate helper files and modular structure.

Multi-Agent Coordinator

Coordinator with specialized sub-agents (e.g., formal and casual greeting team).

Multi-Agent Patterns

Runnable blueprints for Sequential, Parallel, Router, Hierarchical, and Aggregator flows.

Runtime Configuration

How to pass per-request overrides for agents, tools, and MCPs at runtime (e.g., database URLs or planning).

Agent Export & Import

Demonstrates how to serialize and deserialize agent configurations for portability.

Local Execution

Run agents locally without deployment (see Local vs Remotearrow-up-right for feature mapping).


Cookbook Examples

Goal
Guide

Attach native or custom tools to an agent

Attach files, manage artifacts, and reuse chunks

Coordinate sequential, parallel, router, hierarchical, or aggregator flows

Configure Model Context Protocol connectors

Tune language_model_id values and routing strategies

Orchestrate runs from scripts or CI pipelines

Export/import configurations or sync LangFlow flows

Apply PII masking, memory, and tool-output policies

Prepare for multi-account setups and future RBAC

Last updated