FastClaw Docs
Runtime

Sandbox

Execute tools and generated code through Docker, E2B, or Boxlite.

FastClaw runs agent tools in a sandbox when sandboxing is enabled. The sandbox receives a hydrated workspace, mounted skills, selected environment variables, and the configured tool policy.

Backends

BackendUse whenNotes
dockerLocal or self-hosted deploymentsUses long-lived or per-turn containers; supports bind mounts
e2bCloud sandbox executionExposes sandbox ports through E2B URLs
boxliteBoxlite-compatible sandbox executionUses Boxlite API settings

Bootstrap Env

FASTCLAW_SANDBOX_ENABLED
FASTCLAW_SANDBOX_BACKEND
FASTCLAW_SANDBOX_IMAGE
FASTCLAW_SANDBOX_BOXLITE_URL
FASTCLAW_SANDBOX_BOXLITE_CLIENT_ID
FASTCLAW_SANDBOX_BOXLITE_PREFIX

Dashboard runtime settings can also control sandbox enablement, backend, image/template, and network policy.

Workspace Hydration

Before a tool call, FastClaw hydrates:

  • the chat/project workspace
  • global skills under $FASTCLAW_HOME/skills
  • agent-private skills under $FASTCLAW_HOME/agents/<agentId>/agent/skills
  • selected environment variables and credentials

After execution, changed files are synced back to the durable store.

Policy

Tool execution is governed by policy. Keep production agents restrictive by default:

  • limit network access when possible
  • avoid passing broad secrets into the sandbox
  • prefer per-agent or per-tool scoped credentials
  • use object storage for distributed file hydration instead of local-only paths

Standalone Sandbox Commands

fastclaw sandbox create --image thinkany/fastclaw-sandbox:latest
fastclaw sandbox list
fastclaw sandbox connect <container-id>
fastclaw sandbox destroy <container-id>