Back to home@wecode-ai

Wegent

Plan, build, and deliver with an open-source, self-hostable AI workspace for coding, collaboration, and automation.

Stars
765
Language
TypeScript
Created
Jan 10, 2026
Updated
Aug 31, 2026

Introduction

Wegent

An open-source AI work system spanning your local desktop, cloud agents, and remote machines.

English | 简体中文

CI License GitHub Issues

Wegent includes a desktop workbench and a self-hostable web platform. Wegent Desktop works with local projects, files, commands, tests, and code changes. Wegent Web provides browser-based agents, knowledge, automation, and administration. Wegent Backend connects these applications to shared project spaces, models, and execution devices.

Download the latest Wegent Desktop · Documentation · Contributing

Wegent Desktop

Wegent Desktop organizes local coding work by project and task. The task view keeps the conversation, tool activity, tests, changed files, and diffs together; the project-space view provides the board, shared files, automation, and execution status.

A real Wegent Desktop coding task showing the verified result, changed files, and an expanded source-code diff in one workbench

Running and reviewing a local coding task in Wegent Desktop.

A real Wegent Desktop project workspace with its kanban board, project navigation, and a remote-machine test task in progress

A project space in Wegent Desktop with its task board, shared files, automation, and execution status.

Features

  • Desktop workbench — Organize local projects, tasks, sessions, files, tool activity, tests, and diffs.
  • Reusable agents — Combine models, prompts, Skills, knowledge, tools, and collaboration settings.
  • Project spaces — Share task boards, files, discussions, automation, execution history, and deliveries.
  • Multiple execution targets — Run tasks locally, on remote work machines, or with server-managed executors.
  • Self-hosting — Deploy Wegent Web and Backend for team access, APIs, permissions, scheduling, and knowledge services.

Why Wegent

The local coding experience built on Codex is the foundation of Wegent Desktop. It works directly with the code, files, commands, and development environment in your projects. Connect it to Wegent Backend when coding work needs to move beyond one computer or one person. Once connected, the desktop workbench and Web use the same projects, tasks, and execution devices.

  • Run tasks on the right device — Keep using the code, files, commands, and development environment already on a local machine, or run a task for the same project on a remote work machine or server-managed executor.
  • Move a project forward as a team — Project spaces connect task boards, shared files, discussions, execution status, and deliveries instead of leaving conversations and code changes on separate computers.
  • Automate repeated project work — Project spaces can configure automation and execution queues to keep routine work moving.
  • Keep services and data under team control — Self-host Web and Backend for shared access, permissions, model configuration, scheduling, knowledge services, and remote-device management.

If work always stays on one computer, Wegent Desktop provides a familiar Codex coding experience. Connect it to Wegent to extend that experience when tasks must move across people, devices, or a self-hosted environment.

Wegent Web

Wegent Web provides the browser interface for remote agents. Agents can use configured models, knowledge, Skills, and tools while Wegent Backend manages their tasks and execution.

A Wegent remote agent using tools to generate and display a Gantt chart

A Wegent remote agent uses tools to generate a Gantt chart.

How it works

Wework is the Wegent desktop workbench. Electron owns desktop windows, system capabilities, and process management. DeepSeek Harness (DSH) is the embedded application and plugin runtime, and the Wework product UI is composed from a set of DSH plugins. Executor manages tasks and sessions, then drives Codex to perform the actual work in local projects.

flowchart LR
    Electron["Electron<br/>Desktop host"]

    subgraph DSH["DSH Runtime"]
        direction TB
        Core["DSH Core<br/>Plugin discovery, dependency injection, and lifecycle"]
        App["dsh-app-wework<br/>Wework product shell and UI extension points"]
        UI["dsh-ui-*<br/>Tasks, project spaces, settings, apps, and automation"]
        ElectronPlugin["dsh-electron-host<br/>Electron capability bridge"]
        ExecutorPlugin["dsh-executor-runtime<br/>Task execution and event adapter"]
        TerminalPlugin["dsh-terminal-runtime<br/>Local interactive terminals"]

        Core --> App
        Core --> UI
        Core --> ElectronPlugin
        Core --> ExecutorPlugin
        Core --> TerminalPlugin
        App --> UI
    end

    Executor["Executor<br/>Task and session execution"]
    Codex["Codex<br/>Coding agent"]
    Workspace["Local project<br/>Files and commands"]

    Electron -->|"Starts and hosts"| Core
    Electron -->|"Starts and supervises"| Executor
    ElectronPlugin <-->|"Restricted desktop capabilities"| Electron
    UI <-->|"User actions and UI updates"| ExecutorPlugin
    ExecutorPlugin -->|"Create, follow up, approve, cancel"| Executor
    Executor -->|"Status, messages, tool events, results"| ExecutorPlugin
    Executor <-->|"Launch, control, and events"| Codex
    Codex <-->|"Read, modify, and execute"| Workspace
    TerminalPlugin <-->|"PTY"| Workspace

DSH does not execute coding tasks itself. dsh-app-wework defines the product shell and extension points, dsh-ui-* provides the product modules, dsh-electron-host bridges restricted Electron capabilities, dsh-executor-runtime communicates bidirectionally with Executor throughout execution, and dsh-terminal-runtime manages local interactive terminals. Executor is the task execution layer, while Codex is the concrete coding agent it drives.

Wework can also connect to Wegent Backend for shared project spaces, models, and remote execution devices. Wegent Web is a separate browser interface built on the same Backend.

Quick start

Wegent Desktop

  1. Download the latest Wegent Desktop installer and install it.
  2. Open the app and add or select a local project.
  3. Create a task and describe the work to perform.
  4. Review the agent activity, command output, and file changes.

Wegent Web and Backend

To start the self-hosted web application and Backend in standalone mode with Docker:

curl -fsSL https://raw.githubusercontent.com/wecode-ai/Wegent/main/install.sh | bash -s -- --standalone

Open http://localhost:3000 and follow the setup flow to create the administrator password and configure a model. See the Installation Guide and Standalone Mode for other deployment options.

Development

Requires Node.js 20+ and pnpm:

pnpm install
pnpm --filter wework dev

To run the macOS desktop app:

pnpm --filter wework dev:mac

See wework/README.md for desktop development, build, and release instructions. wework/ is the current desktop application source directory.

Repository map

DirectoryResponsibility
wework/Wegent Desktop (Electron, Vite, React)
executor/Local and remote agent task execution environments
frontend/Wegent platform web administration
backend/REST API and core business logic
executor_manager/Executor scheduling and orchestration
chat_shell/Chat runtime
knowledge_runtime/Knowledge retrieval services
knowledge_doc_converter/Document parsing and conversion
shared/Modules shared across services

Documentation

Contributing

Bug reports, documentation improvements, code contributions, and new ways of using Wegent are all welcome.

Contributors

Thanks to everyone who helps Wegent grow.

qdaxb
Axb
Micro66
MicroLee
feifei325
Feifei
FicoHu
FicoHu
icycrystal4
Icycrystal4
kissghosts
Yanhe
cc-yafei
YaFei Liu
moqimoqidea
Moqimoqidea
johnny0120
Johnny0120
parabala
Parabala
sunnights
Jake Zhang
joyway1978
Joyway78
yixiangxx
Yi Xiang
cocowh
Birch
luckjun529-lang
junlong chen
sdadunderscoresdad
+7
2561056571
Xuemin
lvmowei
lvmowei
fengkuizhi
Fengkuizhi
jnhu76
Jm.hu
maquan0927
Just Quan
kerwin612
Kerwin Bryant
DavidLeeUX
Kva
hustfisher
fishermen
earthAlone2026
xiaoqiang
RockysGit
RockysGit
qwertyerge
Erdawang
junbaor
Junbaor
Twelveeee
Twelveeee
fingki
Fingki
flyhope
李枨煊
jolestar
Jolestar
code-wangdi
Code-wangdi
haosenwang1018
Sense_wang
LiDaiyan
Li Daiyan
DeadLion
Jasper Zhong
rayzhang0603
Ray
RichardoMrMu
RichardoMu
Ged0
_
andrewzq777
Andrewzq777
ch15084
Ch15084
gdouyang
Gdouyang
graindt
Graindt
qingchengliu
Qingcheng
Qinxl0921
qinxll
salt-hai
Salt-hai
wxcfox
Wxcfox

Made with ❤️ by WeCode-AI Team