Skillget

OpenGUI

agent
Guvenlik Denetimi
Uyari
Health Gecti
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 27 GitHub stars
Code Uyari
  • process.env — Environment variable access in build.ts
  • process.env — Environment variable access in claude-code-bridge.mjs
  • process.env — Environment variable access in codex-bridge.mjs
  • network request — Outbound network request in dev.ts
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This application provides a desktop and web-based command center for managing multiple AI coding agents. It allows users to run parallel coding sessions, stream responses, and switch between different models and agent backends from a single visual interface.

Security Assessment
Overall risk: Medium. As a tool designed to manage and interact with coding agents, it inherently relies on environment variables to pass API keys and configuration to the various AI backends, which explains the warnings for bridge and build files. There are no hardcoded secrets or dangerous system permissions requested. However, it does make outbound network requests during development, and users should be aware that any tool orchestrating AI agents naturally has access to the prompts, code context, and commands sent to those backends.

Quality Assessment
The project is actively maintained, with its last push occurring today. It uses the standard, permissive MIT license, making it highly accessible for modification and use. While the community footprint is currently small with 27 stars, the repository is well-documented, includes clear build instructions, and the author explicitly states that the project is early but usable and open to community contributions.

Verdict
Use with caution — it is a well-structured and actively maintained project, but as an early-stage orchestrator handling API keys and external AI connections, you should carefully review its bridge scripts before integrating it into sensitive environments.
SUMMARY

Desktop + web command center for OpenCode, Claude Code, Codex, and Pi. Multi-project AI coding sessions with streaming chat, prompt queue, model switching, and MCP tools.

README.md

OpenGUI

Desktop + web command center for coding agents. Run OpenCode, Claude Code, Codex, and Pi across multiple projects with streaming chat, prompt queue, model switching, voice input, and MCP tools.

Latest Release License Stars Downloads Build Status

Download latest release · Why OpenGUI · Supported backends · Build from source

OpenGUI Demo

OpenGUI gives coding-agent users desktop and browser workflow for long sessions. Manage multiple projects visually, run different agent backends from one UI, watch responses stream live, queue prompts while agent works, and switch models or agents without terminal juggling.

Early but usable. Bug reports and PRs welcome.

Why OpenGUI

OpenGUI is for people who like coding agents but want stronger workflow than terminal tabs alone:

  • Run multiple agent backends in one app instead of juggling separate tools
  • Manage multiple projects at once with separate sessions per workspace
  • See streaming responses live with token and context usage
  • Queue prompts while agent is busy instead of waiting to type next step
  • Switch providers, models, agents, and variants from UI
  • Configure MCP tools and skills without leaving app
  • Use voice input with Whisper-compatible transcription endpoint

Highlights

  • Multi-agent workspace for OpenCode, Claude Code, Codex, and Pi
  • Multi-project workspaces for parallel coding sessions
  • Real-time streaming over SSE with live usage tracking
  • Prompt queue that auto-dispatches when assistant becomes idle
  • Model, backend, and agent selection directly from chat workflow
  • Slash commands from prompt box
  • Syntax highlighting + math rendering with Shiki and KaTeX
  • Dark/light theme with system-aware toggle
  • Desktop, web, and Docker deployment options
  • Cross-platform builds for Linux, macOS, and Windows

Supported agent backends

OpenGUI currently supports these coding-agent backends:

  • OpenCode
  • Claude Code
  • Codex
  • Pi

Use one backend or switch between them per workflow.

Download

Grab prebuilt app from latest release:

  • Linux: .deb
  • macOS: .dmg
  • Windows: .exe installer

Requirements

Backend requirements depend on what you use:

  • OpenCode backend: OpenCode CLI installed and available in your PATH
  • Other backends: local CLI/auth/config for that backend available on your machine

Windows prerequisite for OpenCode: OpenCode must be available on your PATH or at %USERPROFILE%\.opencode\bin\opencode.exe.

Note: Windows builds are unsigned. Windows SmartScreen will warn on first launch. Click More info -> Run anyway.

Build from source

Prerequisites

  • Bun v1.2+
  • At least one supported backend configured locally (for example OpenCode CLI in your PATH for OpenCode)
  • Electron installed through project dependencies

Install dependencies:

bun install

No manual config file needed. Connection settings live in UI. Pick backend, connect workspace, start prompting.

Development

Run Electron app with HMR:

bun dev

Run web app with local backend API (projects, git, agents):

bun dev:web

Open http://127.0.0.1:3000. Browser folder picker uses server paths. Set OPENGUI_ALLOWED_ROOTS=/path/to/projects to restrict browsable folders.

Docker

Docker install supports contained mode and host-control mode. Host-control mode uses host CLIs through nsenter while Docker manages web server.

See docs/docker.md for Docker modes and docs/apache.md for Apache reverse proxy + Basic Auth.

Production

Build frontend bundle:

bun run build

Run Electron app in production mode:

bun start

Build and run web app in production mode:

bun start:web

For internet-facing deploys, keep OpenGUI bound to localhost and put Apache or another HTTPS reverse proxy in front.

Distribution

Build Linux .deb:

bun run dist

Build macOS .dmg:

bun run dist:mac

Build Windows .exe installer:

bun run dist:win

Architecture

main.cjs              Electron main process (window management, IPC)
preload.cjs           Preload script (contextBridge API for renderer)
opencode-bridge.mjs    IPC bridge to OpenCode SDK
claude-code-bridge.mjs IPC bridge to Claude Code SDK
codex-bridge.mjs       IPC bridge to Codex SDK
pi-bridge.mjs          IPC bridge to Pi runtime
server/web-server.ts  Bun backend for browser mode (RPC, events, server FS browser)
src/
  index.ts            Renderer-only Bun dev server entry
  index.html          HTML entry point
  frontend.tsx        React entry point + web Electron shim install
  App.tsx             Main app layout
  hooks/
    use-agent-impl-core.tsx  Central agent/workspace state
  components/         UI components (sidebar, messages, prompt box, etc.)
  lib/
    web-electron-api.ts      Browser shim for Electron preload API
  types/              TypeScript type definitions

Configuration

OpenGUI stores connection and UI preferences via the app settings interface.

Voice input (speech-to-text) requires a Whisper-compatible transcription server. Set the endpoint URL in Settings > General > Voice transcription endpoint. The microphone button only appears when an endpoint is configured. The server should accept a multipart POST with an audio file field and return { text, language, duration_seconds }.

Contributing

Contributions are welcome. See CONTRIBUTING.md for guidelines.

Star History

If you find OpenGUI useful, consider giving it a star -- it helps others discover the project.

Star OpenGUI on GitHub

License

MIT

Yorumlar (0)

Sonuc bulunamadi