Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
| Date | Stars |
|---|---|
| 2026-07-24 | 7719 |
| 2026-07-25 | 7721 |
| 2026-07-28 | 7721 |
| 2026-07-30 | 7721 |
| 2026-07-31 | 7725 |
| 2026-08-06 | 7725 |
Today
— stars today
This week
+4 stars this week
This month
— stars this month
Momentum
39.0
growth rate 0.05%/day
<h2 align="center">Agent Squad</h2>
<p align="center">Flexible, lightweight open-source framework for orchestrating multiple AI agents — in the cloud with Python and TypeScript, and now <strong>on device</strong> with Swift.</p>
<p align="center">
<a href="https://www.npmjs.com/package/agent-squad"><img alt="npm" src="https://img.shields.io/npm/v/agent-squad.svg?style=flat-square"></a>
<a href="https://pypi.org/project/agent-squad/"><img alt="PyPI" src="https://img.shields.io/pypi/v/agent-squad.svg?style=flat-square"></a>
<a href="swift/README.md"><img alt="Swift" src="https://img.shields.io/badge/Swift-iOS%2016%20%C2%B7%20macOS%2014-orange.svg?style=flat-square"></a>
<a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/license-Apache%202.0-blue.svg?style=flat-square"></a>
</p>
<h3 align="center">
<img src="https://raw.githubusercontent.com/2fastlabs/agent-squad/main/img/new.png" alt="New" height="20"> Now available in Swift
</h3>
<p align="center">
On-device agent orchestration for iPhone, iPad, and Mac — agents, MCP tools, realtime voice, and tracing, running entirely on device.<br>
<a href="#new-the-swift-runtime--on-device-orchestration"><strong>See what's included ↓</strong></a> · <a href="swift/README.md"><strong>Swift README →</strong></a>
</p>
<p align="center">
<a href="https://2fastlabs.github.io/agent-squad/"><strong>Explore the full documentation</strong></a>
</p>
> **New home:** previously hosted at `awslabs/agent-squad`, the project is now maintained at `2fastlabs/agent-squad` (and was formerly named `multi-agent-orchestrator`). Please update bookmarks, clone URLs, and dependencies.
## What is Agent Squad?
Agent Squad routes each user query to the most suitable of your specialized agents and maintains conversation context across them. You get pre-built agents, classifiers, and storage for quick deployment, plus small, well-defined seams to plug in your own.
- 🧠 **Intelligent intent classification** — route queries by context and content.
- 🌊 **Streaming and non-streaming** agent responses.
- 📚 **Context management** — coherent conversations across agents and sessions.
- 🔧 **Extensible by design** — custom agents, classifiers, storage, and retrievers.
- 📦 **Pre-built agents** — Bedrock, Anthropic, OpenAI, Lex, Lambda, and more.
## Three runtimes, one framework
| Runtime | Requirements |
|---|---|
| [**Python**](#python) | Python 3.11+ |
| [**TypeScript**](#typescript) | Node.js |
| [**Swift**](#swift) — **new** | iOS 16+ / macOS 14+ |
Python and TypeScript maintain feature parity and run anywhere — AWS Lambda, containers, your laptop. The new **Swift runtime** brings the same orchestration model to Apple platforms and runs **entirely on device**: classifier routing, tools (native and [MCP](https://modelcontextprotocol.io)), realtime voice, tracing, and local-first chat storage.
## How it works
1. User input is analyzed by a **Classifier**.
2. The Classifier uses the agents' descriptions and the conversation history to select the best agent for the turn.
3. The selected **Agent** processes the input (calling tools as needed).
4. The **Orchestrator** saves the exchange and returns the response.
## Quick start
### TypeScript
```bash
npm install agent-squad
```
```typescript
import { AgentSquad, BedrockLLMAgent } from "agent-squad";
const orchestrator = new AgentSquad();
orchestrator.addAgent(
new BedrockLLMAgent({
name: "Tech Agent",
description: "Specializes in technology: software, hardware, AI, cybersecurity, cloud.",
streaming: true
})
);
const response = await orchestrator.routeRequest("What is AWS Lambda?", "user123", "session456");
console.log(`> Agent: ${response.metadata.agentName}\n`);
if (response.streaming) {
for await (const chunk of response.output) {
if (typeof chunk === "string") process.stdout.write(chunk);
}
Excerpt of 13,980 characters
Read on GitHub
448
362
104
18
Leandro Damascena · @aws · Portugal
8
Mohamed Amine Ferhi · Netherlands
7
Ashish Patel · Oracle | xIBMers · India
5
4
3
2
2
2
Ikko Eltociear Ashimine · Japan
2
1
1
1
1
1
Octopus · Independent Developer · United States
1
Kapil Sachdeva
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1cb32afc7d0a7c62, topic:ai-agents, topic:agents, topic:agentic-ai