framework-selection

Select the appropriate framework layer for LangChain, LangGraph, or Deep Agents projects.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/dotlab-hq/torque --skill framework-selection-dotlab-hq
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: framework-selection
Source: https://github.com/dotlab-hq/torque/tree/main/.agents/skills/framework-selection
Command: npx skills add https://github.com/dotlab-hq/torque --skill framework-selection-dotlab-hq

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Selecting the correct AI framework layer at the outset avoids misaligned tool usage and ensures the project uses the right primitives for tasks.

Core Features & Use Cases

  • Framework auto-selection: chooses between LangChain, LangGraph, and Deep Agents based on task needs.
  • Guided setup: defines the recommended next skills to invoke after selection.
  • Early architecture alignment: helps teams structure projects for mixed-layer workflows.

Quick Start

Load this skill at the start of your project to route framework selection and set the initial agent strategy.

Frequently Asked Questions about framework-selection

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I choose between LangChain, LangGraph, and Deep Agents for my project?

Choosing the right framework layer involves matching task complexity to primitives: LangChain for simple single-purpose agents, LangGraph for complex control-flow graphs, and Deep Agents for multi-step workflows with persistent memory.

When should I decide the AI agent framework layer for architectural alignment?

You must decide the framework layer at project start. Early architectural alignment ensures correct primitives are used for mixed-layer workflows and influences subsequent skill invocation before any agent code is written.

What is the best way to set up a multi-step workflow with persistent memory?

Use Deep Agents to set up multi-step workflows with persistent memory. This framework layer provides the necessary architectural primitives to manage stateful agent workflows effectively.

Does LangGraph work better than LangChain for complex control-flow graphs?

LangGraph works better for complex control-flow graphs. LangChain is designed for simple single-purpose agents, while LangGraph provides the specialized primitives needed to manage intricate agent state transitions.

Can I use multiple framework layers in the same AI agent project?

Yes, you can use multiple framework layers in the same project. Early framework selection helps teams structure projects for mixed-layer workflows, allowing LangChain, LangGraph, and Deep Agents to operate synergistically.

Why does misaligned tool usage happen in AI agent projects?

Misaligned tool usage happens when the incorrect framework layer is selected at project start. Using the wrong primitives for tasks forces simple agents into complex graphs or overcomplicates basic workflows.