superagentx

<div align="center">

<img src="https://github.com/superagentxai/superagentX/blob/master/docs/images/fulllogo_transparent.png" width="350">


<br/>


**SuperAgentX**: is an open-source, modular agentic AI framework that enables AI agents to plan, act, and execute real-world workflows—with built-in human approval, governance, and auditability.
Unlike traditional chatbots, SuperAgentX is designed for action, not just conversation.



<br/>

[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/release/python-31210/)
[![GitHub Repo stars](https://img.shields.io/github/stars/superagentxai/superagentX)](https://github.com/superagentxai/superagentX)
[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://github.com/superagentxai/superagentX/blob/master/LICENSE)

</div>

## ✨ Why SuperAgentX?

SuperAgentX enables AI agents to:
- Execute multi-step workflows
- Interact with browsers, APIs, databases, tools & MCPs
- Pause for **human approval** before sensitive actions
- Persist execution state, memory, and audit logs

All while keeping humans firmly in control.

# Quick start

```shell
pip install superagentx
```

## 🧠 Core Capabilities

### 🔹 Massive Model & Tool Support
- ✅ **100+ LLMs supported** (OpenAI, Azure OpenAI, DeepSeek, DeepSeek, Bedrock, OSS models)
- ✅ **10,000+ MCP (Model Context Protocol) tools supported**
- ✅ **Browser Agents** using real browser automation (Playwright)

---

### 🔹 Agentic AI (Beyond Chatbots)
Agents can:
- Understand goals
- Plan execution steps
- Call tools dynamically
- Run sequential or parallel workflows
- Retry, reflect, and recover

---

### 🔹 Human-in-the-Loop Governance
A built-in **Human Approval Governance Agent**:
- Pauses sensitive actions
- Requests explicit approval
- Resumes or aborts execution
- Persists decisions for audit

➡️ AI **cannot act blindly**.

---

## 🗄️ Persistent Data Store & Memory

### Supported Data Stores
- 🗃 **SQLite** – lightweight,