EnvHaven

Batteries-included development environment for agentic workflows.

As tools like Claude Code, OpenCode and Codex gain agency, they need full system access to be effective. Running them locally carries risk (rm -rf accidents, credential leaks) and friction (installing complex runtimes).

EnvHaven solves this. It's a remote environment that spins up in seconds, with sane defaults and every major AI coding tool and built-in, fully isolated from your personal machine and pre-configured to bypass permissions out of the box.

Workflow Freedom:

• Browser-only — Deploy the image, open VS Code in your browser, run opencode. Zero setup.
• Local editor + remote AI — Use the Haven CLI to sync your project. Edit in Neovim, Zed, Jetbrains, et al. while agents run in the container. Changes sync in ~200ms.

Why EnvHaven

🛡️ Zero-Risk AI environment
Give autonomous agents full access in a containerized environment. If they break something, nuke the workspace and start over. Your local machine stays untouched.

🖥️ Pick Up Where You Left Off
Start Claude Code on your laptop, close the lid, resume from your desktop—same session, same state. Your AI agents and dev servers keep running while you're away. Come back from any device.

🌲 Evergreen AI Tooling
The landscape moves too fast to manage manually. EnvHaven ships with 12+ AI CLI tools (Claude Code, OpenCode, Aider, Codex, Gemini CLI, Goose, Mistral Vibe, etc.) built-in and ready to run.

🌐 Instant Public URLs (Managed only)
Every managed workspace gets a wildcard *.envhaven.app domain. Deploy a web app, webhook receiver, or Discord bot—live instantly. No ngrok, no tunnels, no DNS.

💾 Persistent & Owned
Unlike ephemeral environments (Codespaces) or walled gardens (Replit), EnvHaven workspaces are persistent Linux environments you own.

⚡ Open Model

• Self-Hosted: Free forever, open-source Docker image and CLI. Run it on your own server.
• Managed ($10/mo): Zero-config hosting with custom domains, always-on workspaces, and no DevOps.

Who It's For

Quick Start

Path A: Browser-Only (Zero Setup)

Deploy the image and code immediately in the browser.

docker run -d \
  --name envhaven \
  -p 8443:8443 \
  -p 2222:22 \
  -e PASSWORD=password \
  -e SUDO_PASSWORD=password \
  ghcr.io/envhaven/envhaven:latest

1. Open https://localhost:8443 (Password: password)
2. Open terminal—you're dropped into a persistent session
3. Run opencode, claude, or aider and start coding

Multiple AI tools at once? Click + in the footer or use the sidebar to create new terminals. Each runs in its own persistent session—close your browser and they keep running.

Path B: Local Editor + Remote AI (Haven CLI)

Use your local editor. Files sync bidirectionally. Agents run in the container.

1. Install Haven CLI

curl -fsSL https://envhaven.com/install.sh | sh

2. Connect to your workspace

cd my-project

# Managed workspace (shorthand)
haven connect . myproject-alice

# Self-hosted container
haven connect . [email protected]:2222

Files sync in ~200ms.

3. Run remote commands

haven opencode     # Runs OpenCode in the container
haven make build   # Runs make in the container
haven npm install  # Runs npm in the container

Self-hosted? You'll need to configure SSH keys first. See SSH Access.

What's Included

The image (ghcr.io/envhaven/envhaven) comes batteries-included.

AI Coding Agents

No API keys are pre-set. You can set them directly in the UI via the bundled EnvHaven Extension in code-server.

You can also provide your own keys via env vars (-e ANTHROPIC_API_KEY=...) or config files.

Zero-Friction Permissions

EnvHaven workspaces are structurally isolated. The default permission prompts from the AI tools add friction without the added value: The container IS the sandbox, so all agents are pre-configured for maximum permissiveness out of the box. No approval prompts, no confirmation dialogs. Agents execute immediately.

You can re-enable prompts per tool by editing the relevant config or unsetting the env var. See the in-workspace AGENTS.md for details.

Runtimes & SDKs

Dev Tools

• Core: zsh, git, curl, wget, zip, unzip
• Utils: ripgrep, fd, jq, sqlite3, htop
• Media: ffmpeg (video/audio), playwright (browser automation)
• Integrations: gh (GitHub CLI), docker (client)

Haven CLI Architecture

The CLI enables a hybrid workflow: Local Editor + Remote Compute.

• Latency: ~200ms bidirectional sync.
• Compatibility: Works with any editor.
• Independence: The sync daemon runs in the background; close the CLI and sync continues.

┌────────────────────────────────────────────────────────────────────────┐
│                            YOUR MACHINE                                │
│                                                                        │
│  ┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐   │
│  │   Local Editor  │     │   Haven CLI     │     │  Sync Daemon    │   │
│  │                 │     │                 │     │                 │   │
│  │  nvim/lazyvim   │     │  haven connect  │     │                 │   │
│  │  emacs/doom     │     │  haven status   │     │  Continuous     │   │
│  │  helix          │     │  haven <cmd>    │     │  bidirectional  │   │
│  │                 │     │                 │     │  ~200ms latency │   │
│  └────────┬────────┘     └────────┬────────┘     └────────┬────────┘   │
│           │                       │                       │            │
│           ▼                       ▼                       ▼            │
│  ┌──────────────────────────────────────────────────────────────────┐  │
│  │                    ~/projects/myapp/                             │  │
│  └──────────────────────────────────────────────────────────────────┘  │
│                                   ▲                                    │
│                                   │                                    │
│                                   ▼                                    │
│  ┌──────────────────────────────────────────────────────────────────┐  │
│  │                    /config/workspace/myapp/                      │  │
│  └──────────────────────────────────────────────────────────────────┘  │
│           ▲                       ▲                       ▲            │
│           │                       │                       │            │
│  ┌────────┴────────┐     ┌────────┴────────┐     ┌────────┴────────┐   │
│  │  Claude Code    │     │    OpenCode     │     │     aider       │   │
│  │  Long-running   │     │  Long-running   │     │  Task-based     │   │
│  │  AI sessions    │     │  AI sessions    │     │  AI sessions    │   │
│  └─────────────────┘     └─────────────────┘     └─────────────────┘   │
│                                                                        │
│                          ENVHAVEN CONTAINER                            │
└────────────────────────────────────────────────────────────────────────┘

Why this matters:

• AI agents need contained compute: They require massive context windows, long-running processes, specific toolchains, and might do dangerous stuff some time.
• You need your editor: You rely on your custom keybindings, themes, and muscle memory.
• Flexibility: Both workflows work independently or together.

Docker Compose

For persistent deployments, use docker-compose.yml with .env:

cp .env.example .env    # Copy and edit with your passwords/API keys
docker compose up -d

Or use inline environment variables for quick testing:

services:
  envhaven:
    image: ghcr.io/envhaven/envhaven:latest
    container_name: envhaven
    environment:
      - PUID=1000
      - PGID=1000
      - TZ=Etc/UTC
      - PASSWORD=password        # Web UI password
      - SUDO_PASSWORD=password   # sudo/SSH password
    volumes:
      - ./config:/config         # Persist home directory
    ports:
      - 8443:8443               # Web UI
      - 2222:22                 # SSH Access
    restart: unless-stopped

See Configuration Reference for all options including AI API keys and SSH setup.

SSH Access

SSH enables the Haven CLI and direct terminal access.

Self-hosted setup: Import your GitHub keys automatically:

environment:
  - PUBLIC_KEY_URL=https://github.com/yourusername.keys
ports:
  - "2222:22"

See Configuration Reference for all SSH options.

Documentation

• AI Tools Guide — Setup guides, API keys, and usage examples for all 12+ AI coding tools
• Configuration Reference — Complete env vars, SSH setup, Docker mods, and compose examples
• Development Guide — Building from source, testing, and contributing
• Haven CLI — CLI source and architecture