OpenClawDocs
View as MarkdownView this page as plain textOpen in ChatGPTAsk questions about this pageOpen in ClaudeAsk questions about this page

FAQ

FAQ

Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS, multi-agent, OAuth/API keys, model failover). For runtime diagnostics, see Troubleshooting. For the full config reference, see Configuration.

This page is an index. The day-to-day FAQ is split across thirteen pages, one per topic. The triage ladder stays on this page; open the page that matches your question.

Page Read it when
What is OpenClaw? You are evaluating OpenClaw, or explaining what it is and who funds it.
Skills and automation You are customizing skills, or a cron job, reminder, or subagent misbehaved.
Sandboxing and memory You are tuning the sandbox, or memory is not persisting.
Where things live on disk You need to find, back up, move, or remove OpenClaw data.
Config basics You are editing config, enabling web search, or recovering from config.apply.
Remote gateways and nodes You run the Gateway on a VPS or another machine, or you are adding a node.
Env vars and .env loading You are setting keys through env or .env, or the service lost them.
Sessions and multiple chats You are managing sessions, resets, context limits, groups, or several bots.
Gateway ports, already running, and remote mode The Gateway will not bind, says it is already running, or you want remote mode.
Logging and debugging You need logs or a service restart, or replies never arrive.
Media and attachments A skill produced an image or PDF but nothing was sent.
Security and access control You are exposing OpenClaw to inbound messages or judging plugin risk.
Chat commands, aborting tasks, and stopping a run A task will not stop, or you are tuning slash commands and the queue.

First 60 seconds if something is broken

  • Quick status

    bash
    openclaw status

    Fast local summary: OS + update, Gateway/service reachability, agents/sessions, provider config + runtime issues (when the Gateway is reachable).

  • Pasteable report (safe to share)

    bash
    openclaw status --all

    Read-only diagnosis with a log tail (tokens redacted).

  • Daemon + port state

    bash
    openclaw gateway status

    Shows supervisor runtime vs RPC reachability, the probe target URL, and which config the service likely used.

  • Deep probes

    bash
    openclaw status --deep

    Live Gateway health probe, including channel probes when supported (requires a reachable Gateway). See Health.

  • Tail the latest log

    bash
    openclaw logs --follow

    If RPC is down, fall back to:

    bash
    tail -f "/tmp/openclaw/openclaw-$(date +%F).log"# Named profile example:tail -f "/tmp/openclaw/openclaw-dev-$(date +%F).log"

    File logs are separate from service logs; see Logging and Troubleshooting.

  • Run the doctor (repairs)

    bash
    openclaw doctor

    Repairs/migrates config and state, then runs health checks. See Doctor.

  • Gateway snapshot (WS-only)

    bash
    openclaw health --jsonopenclaw health --verbose   # shows the target URL + config path on errors

    Asks the running Gateway for a full snapshot. See Health.

    • Quick start and first-run setup

    First-run Q&A - install, onboard, auth routes, subscriptions, initial failures - lives on the First-run FAQ.

    Models, failover, and auth profiles

    Model Q&A - defaults, selection, aliases, switching, failover, auth profiles - lives on the Models FAQ.

    Miscellaneous

    What is the default model for Anthropic with an API key?

    Credentials and model selection are separate. Setting ANTHROPIC_API_KEY (or storing an Anthropic API key in auth profiles) enables authentication, but the actual default model is whatever you configure in agents.defaults.model.primary (for example anthropic/claude-sonnet-4-6 or anthropic/claude-opus-4-6). No credentials found for profile "anthropic:default" means the Gateway could not find Anthropic credentials in the SQLite auth stores available to the running agent.

    Still stuck? Ask in Discord or use the GitHub issue chooser.

    Where each section moved

    Every question heading from the previous single-page version keeps its anchor here, so an existing link such as /help/faq#where-things-live-on-disk still resolves. Each entry points at the page that now holds the answer.

    Was this useful?
    On this page

    On this page