Cette page est affichée en anglais. Une traduction française est en cours.
CLI ToolsMay 14, 2026·2 min de lecture

Codeg — Local AI Coding Workspace (Tauri/Web)

Run Codeg as a standalone server or desktop app to manage local agent workflows, MCP installs, and engineering loops; one-line install is available.

Prêt pour agents

Cet actif peut être lu et installé directement par les agents

TokRepo expose une commande CLI universelle, un contrat d'installation, le metadata JSON, un plan selon l'adaptateur et le contenu raw pour aider les agents à juger l'adaptation, le risque et les prochaines actions.

Native · 94/100Policy : autoriser
Surface agent
Tout agent MCP/CLI
Type
Cli
Installation
Curl|Bash
Confiance
Confiance : Established
Point d'entrée
curl -fsSL https://raw.githubusercontent.com/xintaofei/codeg/main/install.sh | bash
Commande CLI universelle
npx tokrepo install d1858674-c832-55db-bf41-aec7683374db
Introduction

Use Codeg to host a local coding workspace for agents and access it from your browser or as a Tauri desktop app.

Run Codeg as a standalone server or desktop app to manage local agent workflows, MCP installs, and engineering loops; one-line install is available.

Best for: developers who want a self-hosted UI + server for local AI coding workflows, MCP management, and multi-tool integrations

Works with: Linux/macOS server mode (curl install), optional desktop/Tauri mode, Node.js toolchain for development

Setup time: ~5–12 minutes (install script + first run)

Key facts (verified)

  • GitHub: 1,178 stars · 126 forks · pushed 2026-05-14.
  • License: Apache-2.0 · owner avatar + repo URL verified via GitHub API.
  • Entrypoint (README-backed): curl -fsSL https://raw.githubusercontent.com/xintaofei/codeg/main/install.sh | bash.

Main

  • Start with server mode to validate the workflow end-to-end before investing in desktop packaging.
  • Keep agent projects and persisted data on explicit volumes/paths so backups and migrations are predictable.
  • If you expose it on a network, put it behind auth + TLS and treat it like any other internal dev service.

README excerpt (source)

# Codeg

[![Release](https://img.shields.io/github/v/release/xintaofei/codeg)](https://github.com/xintaofei/codeg/releases)
[![License](https://img.shields.io/github/license/xintaofei/codeg)](./LICENSE)
[![Tauri](https://img.shields.io/badge/Tauri-2.x-24C8DB)](https://tauri.app/)
[![Next.js](https://img.shields.io/badge/Next.js-16-black)](https://nextjs.org/)
[![Docker](https://img.shields.io/badge/Docker-ready-2496ED)](./Dockerfile)

<p>
  <strong>English</strong> |
  <a href="./docs/readme/README.zh-CN.md">简体中文</a> |
  <a href="./docs/readme/README.zh-TW.md">繁體中文</a> |
  <a href="./docs/readme/README.ja.md">日本語</a> |
  <a href="./docs/readme/README.ko.md">한국어</a> |
  <a href="./docs/readme/README.es.md">Español</a> |
  <a href="./docs/readme/README.de.md">Deutsch</a> |
  <a href="./docs/readme/README.fr.md">Français</a> |
  <a href="./docs/readme/README.pt.md">Português</a> |
  <a href="./docs/readme/README.ar.md">العربية</a>
</p>

Codeg (Code Generation) is an enterprise-grade multi-agent coding workspace.
It unifies local AI coding agents (Claude Code, Codex CLI, OpenCode, Gemini CLI,
OpenClaw, Cline, etc.) in a desktop app, standalone server, or Docker container — enabling

FAQ

Q: Is there a one-line install? A: The README includes an install.sh script and a codeg-server standalone server mode.

Q: Do I need Tauri? A: Only for the desktop app; server mode runs without a GUI.

Q: What should I secure first? A: Network exposure: add auth/TLS and restrict what directories the service can access.

🙏

Source et remerciements

Source: https://github.com/xintaofei/codeg > License: Apache-2.0 > GitHub: 1,178 stars · 126 forks · pushed 2026-05-14

Fil de discussion

Connectez-vous pour rejoindre la discussion.
Aucun commentaire pour l'instant. Soyez le premier à partager votre avis.

Actifs similaires