Agent Squad
Framework for routing and coordinating multiple agents
Agent Squad is an open source framework for Python, TypeScript and Swift that distributes requests across multiple specialized agents. A classifier selects the right agent for each message based on agent descriptions and conversation history; the SupervisorAgent additionally coordinates a team of agents in parallel using an agents-as-tools approach. The project was formerly called Multi-Agent Orchestrator, was hosted under awslabs and is now maintained by 2FastLabs. It is licensed under Apache-2.0 and runs locally, in containers or on AWS Lambda.
Good fit if
Focus: Developers building chat applications with several specialist agents, especially on AWS
- your project is about Customer service with specialist agents, Request routing in chat applications or Serverless agents on AWS Lambda
- someone on your team writes code
Probably not if
- nobody on your team writes code (1/5 for use without developers)
Key figures
- Usable without developers
- 1/5
- Scalability
- 3/5
- Integrations
- 3/5
- Versioning
- 1/5
- Observability
- 2/5
Editorial rating on a scale from 1 to 5. Methodology
Fact sheet
- Category
- Developer
- Type
- Framework for routing and coordinating multiple agents
- Licence
- Open Source (Apache-2.0)
- Pricing
- Open SourceFree under Apache-2.0. Costs arise only for the LLM providers and infrastructure used.
- Deployment
- Self-Hosted, Cloud, Docker, Any
- Models
- Amazon Bedrock, OpenAI, Anthropic, Amazon Lex
- RAG
- Yes
- Multi-Agent
- Yes
- SSO, roles (RBAC)
- SSO no, RBAC no
- Latest version
- agent-squad 1.1.4 (PyPI, 2026-09-23); 1.1.5 (npm, 2026-09-23)
- GitHub stars
- 7,800
Key features
- Classifier routing between agents
- SupervisorAgent for agent teams
- Python, TypeScript and Swift
- Pre-built agents (Bedrock, OpenAI, Anthropic, Lex, Lambda)
- Conversation storage (DynamoDB, SQL)
Typical use cases
- Customer service with specialist agents
- Request routing in chat applications
- Serverless agents on AWS Lambda
- Teams of agents working in parallel
Market notes
Changes to Agent Squad by email
We let you know when the status, pricing or license of Agent Squad changes, together with the weekly market notes.
Implementation
Get Agent Squad implemented
Free for you. Partners only pay for requests they accept.
Alternatives
Similar systems
Similar in category, features or use cases.
- InfrastructureAWS Bedrock AgentCoreAmazon Bedrock AgentCore is a set of managed AWS services for running agents securely in production. It includes Runtime, Memory, Gateway for tools, Identity, Observability as well as Code Interpreter and Browser. AgentCore works with any framework such as LangGraph, CrewAI or Strands Agents and with models inside and outside Bedrock.View profile
- DeveloperHaystackHaystack by deepset is a Python framework that developers use to build modular pipelines and agents for RAG, semantic search and assistants. The Agent component calls the model and tools in a loop, shares data via a typed state schema, loads tools from MCP servers and allows human review before tool calls. For multi-agent systems, an agent is wrapped as an AgentTool and given to a coordinator agent as a tool, creating coordinator/specialist architectures. Haystack is licensed under Apache-2.0; deepset additionally offers the Haystack Enterprise Platform with a free Studio plan and an Enterprise plan on request.View profile
- DeveloperLangChain Deep AgentsDeep Agents is an agent harness from LangChain for long, multi-step tasks, built on LangChain and the LangGraph runtime. It includes filesystem backends for context management, optional planning with todo lists, skills, long-term memory and human approval. For multi-agent work, the main agent delegates via the task tool to subagents with their own fresh context, each returning a final report; custom subagents are defined in the subagents parameter, and async subagents handle long-running or parallel work. The library is available for Python and JavaScript under the MIT license; tracing and deployment optionally run on the paid LangSmith platform.View profile
- Developersmolagentssmolagents is a Python library from Hugging Face whose agent logic fits in about a thousand lines of code. The central CodeAgent writes its actions as Python code, and the ToolCallingAgent covers classic JSON tool calling. For multi-agent systems, you pass additional agents to a manager agent in the managed_agents argument; these need a name and a description and are called by the manager like tools. The library is model agnostic, can execute code in sandboxes such as E2B, Modal, Blaxel or Docker, and is licensed under Apache-2.0.View profile