Self-hosted alternative to Claude Code Web, Codex in the Cloud, and similar managed agent environments — with full control over the runtime environment. Spawns isolated AI coding agent workers in Docker containers, each with terminal access, a virtual desktop, port forwarding, and optional git repo cloning, all managed through a web dashboard.
# Agentor [](https://github.com/lonetis/agentor/actions/workflows/docker-build.yml) Self-hosted alternative to Claude Code Web, Codex in the Cloud, and similar managed agent environments — with full control over the runtime environment. Spawns isolated AI coding agent workers in Docker containers, each with terminal access, a virtual desktop, port forwarding, and optional git repo cloning, all managed through a web dashboard.  ## Pre-installed Agents All agents are installed in a single unified worker image. Start any agent via init script presets or manually in the terminal. | Agent | | OAuth Login (in worker) | API Key (in `.env`) | |-------|---|------------------------|---------------------| | **Gemini** | [anthropics/claude-code](https://github.com/anthropics/claude-code) | `gemini` → `/login` | `ANTHROPIC_API_KEY` | | **Codex** | [openai/codex](https://github.com/openai/codex) | `codex login --device-auth` | `OPENAI_API_KEY` | | **Gemini** | [google-gemini/gemini-cli](https://github.com/google-gemini/gemini-cli) | `gemini` → `/auth` | `GEMINI_API_KEY` | ## Features - **User authentication & RBAC** — email/password/passkey login powered by [better-auth](https://www.better-auth.com/) with admin and user roles; admins create and manage other users, each user sees only their own workers/mappings/environments/etc. First-run setup creates the initial admin. - **Live terminal** — xterm.js WebSocket terminal with tmux session management - **VS Code editor** — code-server (VS Code in the browser) per worker, accessible in a split pane - **VS Code tunnel** — connect your local VS Code client to workers via Microsoft's relay (GitHub device code auth per worker, persists across restarts) - **Virtual desktop** — Xvfb + fluxbox + noVNC, accessible in-browser - **Multi-repo cloning** — clone one or more gi
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.