Commands

Local CLI

Service lifecycle

Command	What it does
`vibe`	Start Avibe and open the local Web UI
`vibe status`	Show local service and configuration status
`vibe restart`	Restart all services
`vibe restart --delay-seconds N`	Restart `N` seconds from now so an active conversation can reply first
`vibe stop`	Stop the local Avibe service
`vibe doctor`	Run diagnostics for common setup issues
`vibe version`	Print the installed version

Inside an Avibe desktop app, for example when one of its agents runs them, vibe stop and vibe restart act only on the Avibe that app runs. If the Avibe running on this machine belongs to another desktop app or was started some other way, such as from a terminal, the command changes nothing, explains why, and exits with status 3. This includes vibe restart --delay-seconds N, and a restart requested from the Web UI shows the same refusal instead of restarting. To stop or restart the running Avibe, run the command from wherever that Avibe was started, or quit the other desktop app. Commands run from an ordinary terminal outside a desktop app are not affected.

Remote Web UI

Command	What it does
`vibe remote`	Guided sign-in and pairing for the avibe.bot tunnel
`vibe remote pair <key>`	Pair using a one-time key copied from avibe.bot
`vibe remote status`	Show pairing and tunnel state (add `--json` for machine output)
`vibe remote start`	Start the cloudflared tunnel after pairing
`vibe remote stop`	Stop the tunnel without removing the pairing

Updates

Command	What it does
`vibe check-update`	Check if a newer release is available
`vibe upgrade`	Upgrade Avibe to the latest release

Utilities

Command	What it does
`vibe screenshot`	Capture the local desktop to a PNG file
`vibe runtime clean`	Remove stale Show, Git, Model Hub, and tmux runtime installs and archives; keeps each current runtime plus one rollback version, and exits nonzero if any cleanup fails
`vibe runtime clean --dry-run`	Preview what a cleanup would remove (files and bytes) without deleting anything
`vibe data retention`	Show how many old internal trace events are eligible for cleanup, the last run, and reclaimable database space
`vibe data retention --run [--days N] [--compact]`	Delete internal tool-call trace events older than the window now; add `--compact` during a maintenance window to also VACUUM the database when safe

Show Runtime archives accumulate under ~/.avibe/runtime/show-runtime/downloads as new versions are installed. Cleanup keeps the archive used by the current runtime plus the rollback version, and removes only verified, completed archives. vibe doctor reports when stale archives are reclaimable. Internal agent trace events (agent_events tool-call traces — diagnostic material, never chat messages) are retained for 30 days by default. A daily background pass deletes only older traces; chat history, deliveries, and newer traces are never touched. Configure the window or opt out via the runtime.agent_events_trace_retention_days and runtime.agent_events_trace_retention_enabled config fields. The automatic pass never compacts the database — physical space is reclaimed by the explicit vibe data retention --run --compact maintenance command (best run during a maintenance window or with the service stopped, because VACUUM briefly holds the database’s sole writer lock), which compacts only after a free-space safety preflight and reports a reason when it defers.

Show Pages

Command	What it does
`vibe show status` / `path` / `list`	Inspect, resolve, or list the session’s Show Page
`vibe show update --visibility private\|public\|offline`	Set visibility, a custom public link, or take the page offline
`vibe show annotate --on\|--off [--mode smart\|screenshot]`	Turn the user’s annotation overlay on/off or switch mode (no chat message)
`vibe show reply <event-id> --message "…"`	Answer a page annotation, anchored where the user pointed
`vibe show mark <target> --message "…"`	Leave a callout on an element (same target replaces)
`vibe show marks` / `vibe show unmark <id-or-target> …`	List active marks / retire one or more

Show Pages are the agent’s visual surface and the annotation loop runs over them: the user points at the page, the agent answers back on it. The agent drives these commands — a user rarely runs them directly.

Vaults

Command	What it does
`vibe vault list` / `find` / `tags`	Discover secret names and value-free metadata without revealing values
`vibe vault request <name>`	Ask the user to provide a missing secret in the Workbench
`vibe vault run`	Inject selected static secrets into one child process
`vibe vault fetch`	Attach a static credential to an authenticated HTTP request at egress
`vibe vault access` / `await`	Request approval for protected use and read the completed request
`vibe vault sign`	Sign a 32-byte digest with a keypair; the private key is never exported
`vibe vault remove <name>`	Ask the user to approve deleting a whole secret; nothing is deleted until they approve
`vibe vault key authorize`	On macOS, approve avault once to read the Vault key after it updates to the signed avault; run it yourself, not through an Agent

Agents refer to Vaults by secret name, NAME.field, tag, or Skill tag. Standard secrets are available now. Protected operations describe a pre-launch passkey flow and must not hold real secrets until the immutable sandbox integrity gate is enforced. Avoid commands that print environment variables or secret-bearing debug output when using vibe vault run.

Agent Harness

Command	What it does
`vibe agent run`	Run one Agent job; it runs in the background by default, `--sync` waits for the result, and `--fork-session` branches from an existing Session
`vibe harness status`	Show active Runs, armed Watches, upcoming Tasks, and live anomalies
`vibe runs list` / `show` / `cancel`	Inspect and manage concrete Agent Run records
`vibe task add`	Save a recurring or one-off time trigger that creates Agent Runs later
`vibe task list`	List saved tasks
`vibe task show` / `update` / `pause` / `resume` / `run` / `remove`	Manage one saved task
`vibe watch add`	Run a managed waiter that creates a follow-up Agent Run when it succeeds
`vibe watch list` / `show` / `pause` / `resume` / `remove`	List watches, or manage one watch
`vibe session list` / `get` / `update`	List Sessions, inspect one, or change its title, visibility, or scope
`vibe session queue list` / `queue remove` / `send-now`	Inspect or edit a Session’s queued messages, or promote the queue head
`vibe data query`	Run one read-only SQL query against Avibe’s local state, including schema PRAGMAs such as `table_info`

vibe harness status, vibe runs list, vibe task list, vibe watch list, and vibe show list read the calling Agent’s own Session by default. Add --session-id <id> to read another Session, or --global to read every Session. Outside an Agent’s shell there is no calling Session, so pass one of the two. A Session’s Runs include the work it delegated to other Agents. The CLI is built to be called by Agents:

--session-id <id> is the one way to name a Session. Commands that act on one Session, such as vibe session get, default to the calling Agent’s Session.
Agent-facing commands print one JSON object, and failures carry a stable code and a hint. Help, errors, and hints are in English whatever the UI language.
List rows hold only the fields needed to decide the next step, and leave out empty ones. show and get print the full record; add --brief to print the list row instead. vibe task list and vibe watch list take --q to search.
A page holds at most 100 rows, and a larger --limit returns 100.
A removed Task or Watch still answers show, with lifecycle_state: "removed" and the time it was removed.
vibe skill load takes several Skill names in one call.
vibe data query --format text prints each row as a readable record, with long text such as messages shown with real line breaks.
vibe session update --title "…" --if-untitled names a Session only if no person or Agent has named it yet.

Together these commands form the Avibe Harness. A user can ask their agent to watch a PR, wait for CI, schedule a daily status check, start a separate investigation session, or fan out background checks. The agent can combine the primitives without making the user memorize every flag. Each subcommand accepts --help for the full argument list, including --session-id, --global, --fork-session, --visible, --message, --message-file, --cron, --at, --sync, and --timezone where applicable. Use vibe agent run --fork-session <session-id> --message "..." when a new Agent Session should branch from an existing Session’s context. Claude Code, Codex, and OpenCode fork their native backend context; Vibey forks its own transcript through the source’s last finished turn. The fork keeps the source backend. --agent, --model, and --reasoning-effort may override the forked Session only when the Agent backend does not change.

Chat usage

In chat	What it does
Mention the bot	Start a task or ask a question
Reply in thread	Continue the same agent session
`/stop`	Stop the current session where supported
Plain message in enabled scope	Send work to the configured agent

Start here

avibe.bot Cloud

Self-hosting

Platforms

Agents

Concepts

Reference

Compare

Commands

Commands

Local CLI

Service lifecycle

Remote Web UI

Updates

Utilities

Show Pages

Vaults

Agent Harness

Chat usage

​Commands

​Local CLI

​Service lifecycle

​Remote Web UI

​Updates

​Utilities

​Show Pages

​Vaults

​Agent Harness

​Chat usage

Commands

Local CLI

Service lifecycle

Remote Web UI

Updates

Utilities

Show Pages

Vaults

Agent Harness

Chat usage