astron-agent  by iflytek

Enterprise agentic workflow platform for building SuperAgents

Created 9 months ago
8,610 stars

Top 6.0% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

Astron Agent is an enterprise-grade, commercial-friendly platform for developing AI agentic workflows, enabling the creation of next-generation "SuperAgents." It integrates AI orchestration, model management, RPA automation, and team collaboration, offering high-availability deployment to build scalable, production-ready intelligent agent applications and establish a robust AI foundation.

How It Works

The platform employs AI workflow orchestration, model management, and integration of AI, MCP, and RPA tools for cross-system automation. Its architecture emphasizes enterprise-grade reliability and a flexible, open ecosystem compatible with diverse industry models and tools. A key advantage is its native RPA integration, enabling seamless interaction between agents and enterprise systems, and supporting a full "decision to action" loop.

Quick Start & Requirements

The recommended quick start involves Docker Compose. Clone the repository, navigate to the docker/astronAgent directory, copy and edit the .env.example configuration file (refer to docs/DEPLOYMENT_GUIDE_WITH_AUTH.md for details), and start services with docker compose -f docker-compose-with-auth.yaml up -d. Prerequisites include Git, Docker, and Docker Compose. Helm charts are under development. Astron Cloud offers a ready-to-use environment at https://agent.xfyun.cn.

Highlighted Details

  • Enterprise-Grade High Availability: Full-stack capabilities for development, building, optimization, and management, supporting one-click deployment with strong reliability.
  • Intelligent RPA Integration: Enables cross-system process automation, empowering agents with controllable execution for a complete "decision to action" loop.
  • Ready-to-Use Tool Ecosystem: Integrates iFLYTEK Open Platform AI capabilities, validated by millions of developers, supporting plug-and-play integration.
  • Flexible Large Model Support: Offers diverse access methods, from rapid API-based model access to one-click deployment of enterprise-level Model as a Service (MaaS) on-premises clusters.
  • Multi-language Backend: Supports Java, Go, and Python for backend development.

Maintenance & Community

Support is available via GitHub Discussions and Issues. A WeChat Work Group is also provided for community interaction. The project is associated with the iFLYTEK Global 1024 Developer Festival.

Licensing & Compatibility

This project is licensed under the Apache 2.0 License, which permits free use, modification, distribution, and commercial use without any restrictions.

Limitations & Caveats

Helm charts for Kubernetes environments are currently under development and not yet available.

Health Check
Last Commit

1 day ago

Responsiveness

Inactive

Pull Requests (30d)
89
Issues (30d)
18
Star History
82 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.