1. Project Overview

Star Chen Agent

Star Chen Agent is aEnterprise-level, business-friendlyAgentic Workflow development platform, integrating AI workflow orchestration, model management, AI and MCP toolset, RPA automation, and team space features. The platform supportsHighly available deployment, helping enterprises quickly buildScalable deploymentIntelligent entity application, building a future-oriented AI foundation.

2. Open Source License

Licensed under Apache-2.0

3. Screenshots

4. Feature Overview

A corporate-level AI intelligent entity development platform, integrating intelligent RPA technology, enabling intelligent entities not only to think but also to act —— automating the processing of digital and desktop environment workflows.

Why choose Xingchen Agent?

• Stable and reliable
  Core technology consistent with the Xingchen Agent platform, with enterprise-level high reliability, complete high-availability open-source version.
• Cross-system connection
  Native integration of intelligent RPA, efficiently connecting internal and external enterprise systems, achieving Agent and enterprise system interconnection.
• Corporate-level open ecosystem
  Deep adaptation of multiple industry models and tools, supporting custom extension, flexible support for multiple enterprise scenarios.
• Business-friendly
  Based on Apache 2.0 protocol open-source, without any commercial restrictions, freely usable for commercial purposes.

Key features

• Enterprise-level high availability
  Full-link capability coverage of development, construction, optimization, and control, supporting high-availability clusters, one-click deployment, stable and reliable.
• Smart RPA Integration
  Cross-system process automation, enabling agents with high controllable execution power, achieving a complete closed loop from decision-making to action.
• Ready-to-use Ecosystem
  Integrating Baidu's open platform with massive AI capabilities and tools, verified by over 10 million developers, allowing for rapid access without development.
• Flexible Model Support
  Multiple access methods, supporting rapid access and verification of large model APIs to enterprise-level MaaS local clusters for one-click deployment, meeting different scale requirements.

5. Tech Stack

Quick Start

We provide two deployment methods to meet different scenario needs:

Method 1: Docker Compose (Recommended for Quick Experience)

# Clone the project
git clone astron-agent
# Enter the astronAgent directory
cd docker/astronAgent
# Copy the environment variable configuration
cp .env.example .env
Environment variable configuration
vim .env

Please refer to the document: DEPLOYMENT_GUIDE_WITH_AUTH_zh.md


Start all services (including Casdoor)
docker compose -f docker-compose-with-auth.yaml up -d

Service access address

Startup is complete. You can access all services at the following address:

Authentication Service

• Casdoor Management Interface
  http://localhost:8000

AstronAgent

• Application Frontend (nginx proxy)
  http://localhost/

Description

• Default Casdoor login account: admin, password: 123

Method Two: Helm (suitable for Kubernetes environment)

Note: Helm charts are still being perfected, please look forward to it!

For complete deployment instructions and configuration details, please refer to the deployment guide