README.md

March 17, 2026 · View on GitHub

Xagent Banner

What is Xagent?

Describe tasks. Not workflows.

No more flowcharts. No more rigid automation. Just tell Xagent what you want.

❤️ Like Xagent? Give it a star 🌟 to support the development!

Xagent vs OpenClaw

Capability	Xagent	OpenClaw
Core design	Enterprise agent platform	Autonomous personal agent
Security	VM‑level sandbox for safe agent execution	Only a Docker container sandbox — and real usage often requires elevated host permissions
Agent architecture	LLM‑driven planning + efficient multi‑agent orchestration	Mostly linear task execution
Model capability	API-compatible + model-native intelligence*	API or local models used as simple plug-ins (no deep integration)
Knowledge systems	Enterprise RAG / knowledge platforms	Local memory / lightweight RAG
Deployment	Flexible deployment — local, private (on‑prem), or cloud	Mostly local runtime
Multi-tenancy	Tenant‑aware architecture	Primarily single‑user

* Xagent supports both API-based models and open-source models, powered by deep integration with Xinference for model-level optimization.

🎬 See Xagent Think

Give it a goal. Watch it plan, select tools, execute, and deliver.

Xagent Demo

⚡ The Problem

Workflow builders are rigid. They break when requirements change.

You map every decision branch manually
You orchestrate tools by hand
You maintain fragile flow diagrams
You re-engineer when logic changes

🎯 The Xagent Way

With Xagent, you describe the outcome — not the steps.

Plans the task dynamically
Decomposes into executable steps
Selects the right tools automatically
Executes, evaluates, and iterates

🚀 What You Can Build

With Xagent, you don’t design workflows. You describe the task. That’s it.

Just define what you want done — and Xagent plans, decomposes, selects tools, and executes.

Build Anything You Can Describe:

Domain	Examples
Content Creation	Automated PPT generation, marketing posters, creative design assets
Research & Analysis	Deep analysis reports, research summaries, data synthesis
Enterprise Automation	AI copilots for internal teams, knowledge assistants, task automation
Business Intelligence	Data reporting automation, SaaS features, multi-step reasoning systems
Knowledge Work	Document processing, information extraction, structured outputs

If you can clearly describe the goal, Xagent can turn it into an executable system.

All powered by one unified runtime.

🚀 Quick Start

Get started in 3 minutes

1️⃣ Clone and configure

git clone https://github.com/xorbitsai/xagent.git
cd xagent
cp example.env .env

2️⃣ Start with Docker

docker compose up -d

To enable sandbox (requires Linux or WSL2 with KVM support):

docker compose -f docker-compose-sandbox.yml up -d

3️⃣ Open in browser

http://localhost:80

On first startup, Xagent redirects to /setup.

Create the first administrator account there to complete initialization.

If the admin password is forgotten, reset it via CLI:

python -m xagent.web.reset_admin_password --username <admin_username>

That's it. Xagent is now running.

✨ Core Features

🧠 Dynamic Planning Engine

Unlike traditional workflow tools, Xagent plans tasks dynamically at runtime.

Automatic task decomposition
Plan → Execute → Reflect loops
Conditional branching
Multi-step reasoning

No static flows. No brittle chains.

🔌 Tool & Model Orchestration

Xagent connects to your entire stack:

OpenAI, Anthropic and other LLM providers
Self-hosted models via Xinference
External APIs
Knowledge bases (RAG)
Internal enterprise systems

It selects and orchestrates tools automatically during execution.

⚡ Instant Execution Mode

For simple use cases, run tool-enabled LLM calls instantly.

No configuration overhead
Chat-style assistants
Embedded AI features

Start simple. Scale when needed.

📊 Observability & Control

Built for real production use:

Task lifecycle tracking
Token usage monitoring
Execution state management
Multi-user support

Operate agents like real systems — not demos.

🎬 Xagent in Action

Watch Xagent plan, execute, and deliver results in real-time.

Xagent in Action

Stay Ahead

Xagent is actively developed and rapidly evolving.

Stay Ahead

Follow our progress:

⭐ Star us on GitHub to stay updated
🐛 Report issues and request features
💬 Join our community discussions

🏢 Deployment Options

Xagent supports:

Self-hosted deployment
Private cloud environments
On-premise enterprise infrastructure
Docker-based setup

You control your models, data, and infrastructure.

🏗 Architecture Overview

Xagent separates core responsibilities:

Layer	Responsibility
Agent Definition	Intent & constraints
Planning Engine	Dynamic decomposition
Execution Runtime	Orchestration layer
Tool Layer	Integrations & actions
Model Layer	LLM & inference backend