Summary

Wegent is an open-source AI-native operating system designed to define, organize, and run agentic AI workflows at scale. It empowers users to build sophisticated AI applications, from coding assistants to data analysis platforms, by providing a standardized framework for orchestrating intelligent agents. The platform aims to simplify the creation and management of complex AI agent ecosystems for developers and researchers.

How It Works

Wegent employs a Kubernetes-style declarative API and Custom Resource Definition (CRD) patterns to manage AI agents. Users define personalized agent teams, their "souls" (Ghosts), AI model configurations, and executable programs (Shells) via YAML files and a web UI. These components form "Bots," which are then organized into "Teams" with defined collaboration models. This approach offers a standardized, scalable, and configurable method for deploying and managing diverse AI agent functionalities, supporting multiple execution engines like Agno and Claude Code.

Quick Start & Requirements

To get started, clone the repository and run docker-compose up -d. Prerequisites include Docker and Docker Compose. Key documentation links are available for Quick Start (docs/en/getting-started/quick-start.md) and comprehensive Documentation (docs/en/README.md). Users will need to configure GitHub Access Tokens and potentially API keys for specific AI runtimes.

Highlighted Details

• Configuration-Driven Teams: Define and manage agent teams using YAML configurations and a web UI, requiring no secondary development.
• Multi-Execution Engines: Supports both dialogue and coding modes through underlying engines like Agno and Claude Code.
• Isolated Sandbox Environments: Each agent team operates within an independent sandbox, allowing simultaneous execution of multiple teams.
• Advanced Collaboration Modes: Facilitates complex workflows through dialogue modes such as parallel and leader-based agent interactions.
• AI Coding Integration: Seamlessly integrates with code services like GitHub and GitLab for AI-driven development tasks.

Maintenance & Community

The project acknowledges contributions from several individual developers and is maintained by the WeCode-AI Team. Support is primarily handled through GitHub Issues. No explicit links to community channels like Discord or Slack, or a public roadmap, are provided in the README.

Licensing & Compatibility

The project's license is not explicitly stated in the provided README. This lack of clear licensing information presents a significant adoption barrier, particularly for commercial use or integration into closed-source projects.

Limitations & Caveats

The absence of a specified open-source license is the most critical limitation. Dify integration is noted as a planned feature, indicating it is not yet available. Configuration for specific AI runtimes, such as Claude Code, requires careful setup of environment variables.