TUI
remoteclaw tui
Open the terminal UI connected to the Gateway, or run it in local embedded mode.
Related:
- TUI guide: TUI
Options
| Flag | Default | Description |
|---|---|---|
--local | false | Run against the local embedded agent runtime instead of a Gateway. |
--url <url> | gateway.remote.url from config | Gateway WebSocket URL. |
--token <token> | (none) | Gateway token if required. |
--password <pass> | (none) | Gateway password if required. |
--session <key> | main (or global when scope is global) | Session key. Inside an agent workspace it auto-selects that agent unless prefixed. |
--deliver | false | Deliver assistant replies through configured channels. |
--thinking <level> | (model default) | Thinking level override. |
--message <text> | (none) | Send an initial message after connecting. |
--timeout-ms <ms> | agents.defaults.timeoutSeconds | Agent timeout. Invalid values log a warning and are ignored. |
--history-limit <n> | 200 | History entries to load on attach. |
Aliases: remoteclaw chat and remoteclaw terminal invoke the same command with --local implied.
Notes:
chatandterminalare aliases forremoteclaw tui --local.--localcannot be combined with--url,--token, or--password.tuiresolves configured gateway auth SecretRefs for token/password auth when possible (env/file/execproviders).- When launched from inside a configured agent workspace directory, TUI auto-selects that agent for the session key default (unless
--sessionis explicitlyagent:<id>:...). - Local mode uses the embedded agent runtime directly. Most local tools work, but Gateway-only features are unavailable.
- Local mode adds
/auth [provider]inside the TUI command surface. - Plugin approval gates still apply in local mode. Tools that require approval prompt for a decision in the terminal; nothing is silently auto-approved because the Gateway is not involved.
Examples
remoteclaw chatremoteclaw tui --localremoteclaw tuiremoteclaw tui --url ws://127.0.0.1:18789 --token <token>remoteclaw tui --session main --deliverremoteclaw chat --message "Compare my config to the docs and tell me what to fix"# when run inside an agent workspace, infers that agent automaticallyremoteclaw tui --session bugfixConfig repair loop
Use local mode when the current config already validates and you want the embedded agent to inspect it, compare it against the docs, and help repair it from the same terminal:
If remoteclaw config validate is already failing, use remoteclaw configure or
remoteclaw doctor --fix first. remoteclaw chat does not bypass the invalid-
config guard.
remoteclaw chatThen inside the TUI:
!remoteclaw config file!remoteclaw docs gateway auth token secretref!remoteclaw config validate!remoteclaw doctorApply targeted fixes with remoteclaw config set or remoteclaw configure, then
rerun remoteclaw config validate. See TUI and Config.