🚀 An open-source AI-native operating system to define, organize, and run intelligent agent teams
English | 简体中文
| 💬 Chat Mode | 💻 Code Mode | 📚 Knowledge Mode (Experimental) |
|---|---|---|
| LLM: Supports Claude / OpenAI / Gemini and other mainstream models Multimodal: Supports automatic parsing of images / PPT / Word / PDF / Excel files Web Search: Supports integration with various search engines Deep Research: Supports deep research mode with automatic search, organization, and report generation Error Correction: Multiple AIs automatically detect and correct errors in responses Follow-up Mode: AI proactively asks clarifying questions to ensure accurate understanding Extensions: Supports Skill packages / MCP tools / Custom tools |
Multi-platform Integration: Supports GitHub / GitLab / Gitea / Gitee / Gerrit platforms Automated AI Workflow: Branch → Code → Commit → PR automation Requirement Clarification: AI proactively asks questions to ensure accurate understanding Wiki Generation: Automatic codebase documentation generation |
RAG Retrieval: Vector / Keyword / Hybrid retrieval Storage Backends: Elasticsearch / Qdrant Document Parsing: PDF / Markdown / DOCX / Code files Wiki: Automatic codebase documentation generation |
- Agent Creation Wizard: 4-step creation: Describe requirements → AI asks questions → Real-time fine-tuning → One-click create
- Collaboration Modes: 4 out-of-the-box multi-Agent collaboration modes (Sequential/Parallel/Router/Loop), flexible combination of multiple Bots
- Skill Support: Dynamically load skill packages to improve Token efficiency
- MCP Tools: Model Context Protocol for calling external tools and services
- Execution Engines: Supports ClaudeCode / Agno sandboxed isolation, Dify API proxy, Chat direct mode - 4 execution engines
- YAML Config: Kubernetes-style CRD for defining Ghost / Bot / Team / Skill
- API: Provides OpenAI-compatible interface for easy integration with other systems
git clone https://github.com/wecode-ai/wegent.git && cd wegent
docker-compose up -d
# Open http://localhost:3000Optional: Enable RAG features with
docker compose --profile rag up -d
| Team | Purpose |
|---|---|
| chat-team | General AI assistant + Mermaid diagrams |
| translator | Multi-language translation |
| dev-team | Git workflow: branch → code → commit → PR |
| wiki-team | Codebase Wiki documentation generation |
Frontend (Next.js) → Backend (FastAPI) → Executor Manager → Executors (ClaudeCode/Agno/Dify/Chat)
Core Concepts:
- Ghost (prompt) + Shell (environment) + Model = Bot
- Multiple Bots + Collaboration Mode = Team
See Core Concepts | YAML Spec
We welcome contributions! Please see our Contributing Guide for details.
- 🐛 Issues: GitHub Issues
Thanks to the following developers for their contributions and efforts to make this project better. 💪
Axb |
Feifei |
MicroLee |
YaFei Liu |
Johnny0120 |
Moqimoqidea |
Yanhe |
Joyway78 |
Xuemin |
Junbaor |
Fengkuizhi |
Jolestar |
Andrewzq777 |
Graindt |
Made with ❤️ by WeCode-AI Team