skills.rest
jaydeland
jaydelandCOMMUNITY
Explore all skills by this author →
Website𝕏@jaydelandGitHub

strands-multi-agent

Orchestrates multiple AI agents via sequential, graph, swarm, or agents-as-tools patterns in Python.

Updated Mar 20, 2026
Search Tags:#multi-agent#orchestration#swarm#graph-patterns#strands#python-sdk#agents-as-tools
One-click install
npx skills add https://github.com/jaydeland/Tony --skill strands-multi-agent
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: strands-multi-agent
Source: https://github.com/jaydeland/Tony/tree/main/.claude/skills/strands-multi-agent
Command: npx skills add https://github.com/jaydeland/Tony --skill strands-multi-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Strands multi-agent orchestration addresses the challenge of coordinating multiple AI agents to work together on complex tasks without requiring bespoke code for every workflow. It enables building robust orchestration patterns and shared-state collaboration across agents.

Core Features & Use Cases

  • Four orchestration patterns: Sequential, Graph, Swarm, and Agents-as-Tools.
  • Shared state propagation, task history, and role-based agent delegation.
  • Use cases include building end-to-end workflows, dynamic handoffs, and scalable agent teams in Python.

Quick Start

Instantiate the Strands orchestrator with a set of agents and run a simple sequential workflow.

Frequently Asked Questions about strands-multi-agent

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

FAQPage Schema
How do I orchestrate multiple AI agents to collaborate on complex tasks in Python?▼

You can orchestrate multi-agent collaboration in Python by applying sequential, graph, swarm, or agents-as-tools patterns. This enables shared state, task history, and role-based delegation without requiring bespoke workflow code.

What multi-agent orchestration patterns are available for coordinating AI workflows?▼

Available orchestration patterns include sequential workflows, graph-based routing, dynamic swarm handoffs, and agents-as-tools delegation. These patterns support shared state propagation and scalable agent teams.

How do I set up shared state and streaming across a swarm of AI agents?▼

Shared state and event streaming across agent swarms are configured through the Strands Python SDK. You instantiate the orchestrator with your agents to propagate state and stream events during task execution.

Do I need Python 3.10 and the Strands SDK to build multi-agent workflows?▼

Yes, building multi-agent workflows requires Python 3.10 or later and the strands-agents Python SDK. You also need a configured environment for your model providers and any optional tool packages.

Can I implement dynamic task handoffs without writing bespoke orchestration code?▼

Yes, dynamic task handoffs are supported through built-in swarm and graph orchestration patterns. These patterns manage role-based agent delegation automatically without requiring custom workflow code.

What is the difference between sequential and graph orchestration patterns for AI agents?▼

Sequential orchestration processes agents in a linear chain, while graph orchestration routes tasks dynamically across agents based on defined relationships. Both operate within the same shared-state framework.

Related Skills

Explore More Software Engineering Skills→
nesihaver-ILnesihaver-IL

aws-strands

Build model-agnostic AI agents with ReAct reasoning and multi-agent orchestration.

Community
Intermediate
augustsclaugustscl
2

lark-event

Stream Lark Open Platform events to NDJSON via WebSocket subscription.

Community
Advanced
Montte-erpMontte-erp
6

tanstack-ai

Stream AI model outputs with tool calling and Zod-validated structured data.

Official
Advanced
LazyAGILazyAGI
3.9k

lazyllm-skill

Build and orchestrate multi-agent AI applications with LazyLLM.

Official
Advanced