Manage sandbox runtimes for isolated agent execution.

Overview

Genesis can run agents in isolated sandbox runtimes for security. The sandbox commands help you inspect and recreate those runtimes after updates or configuration changes.

Today that usually means:

  • Docker sandbox containers
  • SSH sandbox runtimes when agents.defaults.sandbox.backend = "ssh"
  • OpenShell sandbox runtimes when agents.defaults.sandbox.backend = "openshell"

For ssh and OpenShell remote, recreate matters more than with Docker:

  • the remote workspace is canonical after the initial seed
  • genesis sandbox recreate deletes that canonical remote workspace for the selected scope
  • next use seeds it again from the current local workspace

Commands

genesis sandbox explain

Inspect the effective sandbox mode/scope/workspace access, sandbox tool policy, and elevated gates (with fix-it config key paths).

genesis sandbox explain
genesis sandbox explain --session agent:main:main
genesis sandbox explain --agent work
genesis sandbox explain --json

genesis sandbox list

List all sandbox runtimes with their status and configuration.

genesis sandbox list
genesis sandbox list --browser  # List only browser containers
genesis sandbox list --json     # JSON output

Output includes:

  • Runtime name and status
  • Backend (docker, openshell, etc.)
  • Config label and whether it matches current config
  • Age (time since creation)
  • Idle time (time since last use)
  • Associated session/agent

genesis sandbox recreate

Remove sandbox runtimes to force recreation with updated config.

genesis sandbox recreate --all                # Recreate all containers
genesis sandbox recreate --session main       # Specific session
genesis sandbox recreate --agent mybot        # Specific agent
genesis sandbox recreate --browser            # Only browser containers
genesis sandbox recreate --all --force        # Skip confirmation

Options:

  • --all: Recreate all sandbox containers
  • --session <key>: Recreate container for specific session
  • --agent <id>: Recreate containers for specific agent
  • --browser: Only recreate browser containers
  • --force: Skip confirmation prompt

Important: Runtimes are automatically recreated when the agent is next used.

Use Cases

After updating a Docker image

# Pull new image
docker pull genesis-sandbox:latest
docker tag genesis-sandbox:latest genesis-sandbox:bookworm-slim

# Update config to use new image
# Edit config: agents.defaults.sandbox.docker.image (or agents.list[].sandbox.docker.image)

# Recreate containers
genesis sandbox recreate --all

After changing sandbox configuration

# Edit config: agents.defaults.sandbox.* (or agents.list[].sandbox.*)

# Recreate to apply new config
genesis sandbox recreate --all

After changing SSH target or SSH auth material

# Edit config:
# - agents.defaults.sandbox.backend
# - agents.defaults.sandbox.ssh.target
# - agents.defaults.sandbox.ssh.workspaceRoot
# - agents.defaults.sandbox.ssh.identityFile / certificateFile / knownHostsFile
# - agents.defaults.sandbox.ssh.identityData / certificateData / knownHostsData

genesis sandbox recreate --all

For the core ssh backend, recreate deletes the per-scope remote workspace root on the SSH target. The next run seeds it again from the local workspace.

After changing OpenShell source, policy, or mode

# Edit config:
# - agents.defaults.sandbox.backend
# - plugins.entries.openshell.config.from
# - plugins.entries.openshell.config.mode
# - plugins.entries.openshell.config.policy

genesis sandbox recreate --all

For OpenShell remote mode, recreate deletes the canonical remote workspace for that scope. The next run seeds it again from the local workspace.

After changing setupCommand

genesis sandbox recreate --all
# or just one agent:
genesis sandbox recreate --agent family

For a specific agent only

# Update only one agent's containers
genesis sandbox recreate --agent alfred

Why is this needed?

Problem: When you update sandbox configuration:

  • Existing runtimes continue running with old settings
  • Runtimes are only pruned after 24h of inactivity
  • Regularly-used agents keep old runtimes alive indefinitely

Solution: Use genesis sandbox recreate to force removal of old runtimes. They'll be recreated automatically with current settings when next needed.

Tip: prefer genesis sandbox recreate over manual backend-specific cleanup. It uses the Gateway’s runtime registry and avoids mismatches when scope/session keys change.

Configuration

Sandbox settings live in ~/.genesis/genesis.json under agents.defaults.sandbox (per-agent overrides go in agents.list[].sandbox):

{
  "agents": {
    "defaults": {
      "sandbox": {
        "mode": "all", // off, non-main, all
        "backend": "docker", // docker, ssh, openshell
        "scope": "agent", // session, agent, shared
        "docker": {
          "image": "genesis-sandbox:bookworm-slim",
          "containerPrefix": "genesis-sbx-",
          // ... more Docker options
        },
        "prune": {
          "idleHours": 24, // Auto-prune after 24h idle
          "maxAgeDays": 7, // Auto-prune after 7 days
        },
      },
    },
  },
}

Related