DISCOVER THE FUTURE OF AI AGENTS

Wegent

Added Feb 24, 2026
Agent & Tooling
Open Source
PythonTypeScriptWorkflow AutomationDockerMulti-Agent SystemAI AgentsAgent FrameworkAgent & ToolingModel & Inference FrameworkDeveloper Tools & CodingAutomation, Workflow & RPA

An open-source AI-native operating system that enables intelligent agent team orchestration, cloud code execution, and automated task scheduling through Ghost/Shell/Model architecture and Pipeline/Route/Coordinate/Collaborate patterns.

Core Architecture#

Bot Assembly Formula: Ghost (Persona) + Shell (Executor) + Model = Bot

  • Ghost (Persona): Defines AI role and behavior logic
  • Shell (Executor): Defines execution environment and methods
  • Model: Pluggable LLM brain (OpenAI, Anthropic, DeepSeek, GLM, etc.)

Five Core Modules#

  1. Chat (AI Dialogue): Multi-model compatible dialogue, group chat, attachment parsing, Follow-up/Correction modes, mem0 long-term memory, sandbox execution
  2. Code (Cloud Coding Engine): Parallel cloud coding tasks, requirement clarification, Git integration (GitHub/GitLab/Gitea/Gerrit), MCP/Skill configuration
  3. Follow (AI Task Trigger): Scheduled/event-driven execution, info stream generation, conditional filtering
  4. Knowledge (AI Document Library): Multi-format document management, NotebookLM mode Q&A, knowledge citation
  5. Customization (Fully Configurable): Web-based agent creation, agent wizard, group sharing

Four Collaboration Patterns#

PatternDescriptionExample
PipelineBots work sequentially, passing resultsDeveloper → Reviewer → Tester
RouteLeader Bot dispatches tasks to best-fit BotLeader → {Frontend | Backend | Database}
CoordinateLeader coordinates parallel work and mergesLeader → [Analyst, Data, Report] → combine
CollaborateAll Bots share context and freely discuss[Bot A ↔ Bot B ↔ Bot C]

Built-in Agent Teams#

  • chat-team: General AI assistant + Mermaid diagrams
  • translator: Multi-language translation
  • dev-team: Complete Git workflow (branch → code → commit → PR)
  • wiki-team: Repository Wiki documentation generation

Executor Types#

ExecutorBest Use Case
ChatQuick dialogue, Q&A
CodeProgramming tasks, code generation
AgnoMulti-agent collaboration
DifyWorkflow automation

Quick Deployment#

# One-click install
curl -fsSL https://raw.githubusercontent.com/wecode-ai/Wegent/main/install.sh | bash

# Optional: Enable RAG feature
docker compose --profile rag up -d

Access: http://localhost:3000

Configuration Methods#

  • Web UI: Visual configuration of Prompts, MCP, Skills, and multi-agent collaboration
  • YAML (CRD style): Kubernetes-style definitions for Ghost/Bot/Team/Skill
  • API: OpenAI-compatible interface for easy system integration

Tech Stack#

  • Backend: Python, FastAPI
  • Frontend: TypeScript, Next.js
  • Runtime: Docker, E2B (Sandbox)
  • Protocol Support: MCP (Model Context Protocol), E2B Sandbox
  • License: Apache-2.0

Related Projects

View All

STAY UPDATED

Get the latest AI tools and trends delivered straight to your inbox. No spam, just intelligence.