CLI
The Orfyn CLI lets you manage agents from your terminal. It's the same interface exposed by the daemon's API, so anything you can do in the app you can do from the command line.
Agent orchestration: You can tell coding agents to use the Orfyn CLI to spawn and manage other agents. Orfyn recognizes the calling agent, so CLI-created workers get the same workspace and parent defaults as MCP-created workers.
Quick reference
orfyn run "fix the tests" # Start an agent
orfyn ls # List running agents
orfyn attach <id> # Stream agent output
orfyn send <id> "also fix linting" # Send follow-up task
orfyn logs <id> # View agent timeline
orfyn stop <id> # Stop an agent
Running agents
Use orfyn run to start a new agent with a task:
orfyn run "implement user authentication"
orfyn run --provider codex "refactor the API layer"
orfyn run --background "run the focused test suite"
orfyn run --new-workspace worktree --worktree-mode branch-off --new-branch feature/x --base main "implement feature X"
orfyn run --workspace <workspace-id> "review the current diff"
orfyn run --output-schema schema.json "extract release notes"
orfyn run --output-schema '{"type":"object","properties":{"summary":{"type":"string"}},"required":["summary"]}' "summarize release notes"
From a human shell, a bare orfyn run creates a new local workspace for the current directory. Use --workspace <id> to add the agent to an existing workspace, or --new-workspace local|worktree to explicitly create a separate workspace for the run.
Worktree creation accepts --worktree-mode branch-off|checkout-branch|checkout-pr plus the matching --new-branch/--base, --branch, or --pr-number/--forge options. Use --worktree-slug to choose the managed directory slug.
When an existing Orfyn agent runs the same command, Orfyn recognizes it through ORFYN_AGENT_ID. Without explicit placement, the new agent becomes its subagent in the same workspace. --workspace can place that subagent elsewhere without changing its parent.
Use --output-schema to return only matching JSON output. You can pass a schema file path or an inline JSON schema object. This mode cannot be used with --background.
By default, orfyn run waits for completion. Use --background to return immediately while the agent keeps running.
Workspaces
Create a workspace independently when you want to prepare its files before starting an agent:
orfyn workspace create --isolation local --path ~/dev/my-app --title main
orfyn workspace create \
--isolation worktree \
--path ~/dev/my-app \
--mode branch-off \
--new-branch feature/auth \
--worktree-slug feature-auth \
--base main
orfyn workspace create \
--isolation worktree \
--path ~/dev/my-app \
--mode checkout-branch \
--branch feature/existing \
--worktree-slug existing-copy
orfyn workspace create \
--isolation worktree \
--path ~/dev/my-app \
--mode checkout-pr \
--pr-number 2186
Then list, use, or archive it:
orfyn workspace ls
orfyn run --workspace <workspace-id> "implement authentication"
orfyn workspace archive <workspace-id>
Add --forge <name> to PR checkout when Orfyn cannot infer the forge from the source checkout. See Git worktrees for setup hooks and services.
Workspace scripts
List, start, and stop the scripts configured in a workspace's orfyn.json:
orfyn script ls
orfyn script start web
orfyn script stop web
By default, Orfyn selects the workspace whose directory is the current directory. Pass --cwd <path> to select a different directory, or --workspace <workspace-id> when a directory has multiple workspaces. These commands also accept --host and the standard output options such as --json.
The output includes each script's lifecycle and supervised terminal ID. Services also include their assigned port, proxy URL, and health. See Git worktrees for orfyn.json configuration.
Listing agents
orfyn ls # Running agents in current directory
orfyn ls -a # Include completed/stopped agents
orfyn ls -g # All directories
orfyn ls -a -g --json # Full list as JSON
Streaming output
Use orfyn attach to stream an agent's output in real-time:
orfyn attach abc123 # Attach to agent (Ctrl+C to detach)
Agent IDs can be shortened, abc works if it's unambiguous.
Sending messages
Send follow-up tasks to a running or idle agent:
orfyn send <id> "now run the tests"
orfyn send <id> --image screenshot.png "what's wrong here?"
orfyn send <id> --no-wait "queue this task"
Viewing logs
orfyn logs <id> # Full timeline
orfyn logs <id> -f # Follow (streaming)
orfyn logs <id> --tail 10 # Last 10 entries
orfyn logs <id> --filter tools # Only tool calls
Waiting for agents
Block until an agent finishes its current task:
orfyn wait <id>
orfyn wait <id> --timeout 60 # 60 second timeout
Useful in scripts or when one agent needs to wait for another.
Schedules
Run an agent on a cron schedule. The CLI also accepts simple cadence presets and compiles them to cron. See Schedules from the CLI for the full reference.
orfyn schedule create --every 30m --cwd ~/dev/my-app "Continue the refactor and leave a note."
orfyn schedule ls
orfyn schedule pause <id>
Permissions
Agents may request permission for certain actions. Manage these from the CLI:
orfyn permit ls # List pending requests
orfyn permit allow <id> # Allow all pending for agent
orfyn permit deny <id> --all # Deny all pending
Agent modes
Change an agent's operational mode (provider-specific):
orfyn agent mode <id> --list # Show available modes
orfyn agent mode <id> bypass # Set bypass mode
orfyn agent mode <id> plan # Set plan mode
orfyn agent detach <id> # Make a subagent top-level
Detaching is an explicit lifecycle action, not a creation flag. The agent keeps running; only its relationship to its parent changes.
Daemon management
orfyn daemon start # Start the daemon
orfyn daemon start --web-ui # Start and serve the bundled web UI
orfyn daemon status # Check status
orfyn daemon stop # Stop the daemon
Use ORFYN_HOME to run multiple isolated daemon instances.
Connecting to a remote daemon
--host accepts either a local target (host:port, a unix socket, or a Windows pipe) or a pairing offer URL, the same https://app.orfyn.in/#offer=... link the mobile app uses for QR pairing. With an offer URL the CLI connects through the Orfyn relay with end-to-end encryption, so you can drive a daemon on another machine without exposing it to the network.
Get an offer URL from the daemon you want to control:
orfyn daemon pair --json # prints { url, qr, ... }
Use it from anywhere:
orfyn ls --host 'https://app.orfyn.in/#offer=eyJ2IjoyLC...'
orfyn run --host "$OFFER_URL" "fix the failing tests"
You can also set it once via ORFYN_HOST instead of passing --host on every command.
Multi-agent workflows
The CLI is designed to be used by agents themselves. You can instruct an agent to spawn sub-agents for parallel work:
# Agent A spawns Agent B and waits for it
agent_id=$(orfyn run --background --quiet --title api-agent "implement the API")
orfyn wait "$agent_id"
orfyn logs "$agent_id" --tail 5
Because Agent A's ID is present in the environment, Agent B is created as its subagent in the same workspace unless --workspace is specified.
Simple implement + verify loop:
# Requires jq
while true; do
orfyn run --provider codex "make the tests pass" >/dev/null
verdict=$(orfyn run --provider claude --output-schema '{"type":"object","properties":{"criteria_met":{"type":"boolean"}},"required":["criteria_met"],"additionalProperties":false}' "ensure tests all pass")
if echo "$verdict" | jq -e '.criteria_met == true' >/dev/null; then
echo "criteria met"
break
fi
done
This pattern enables hierarchical task decomposition, a lead agent can break down work, delegate to specialists, and synthesize results.
Output formats
Most commands support multiple output formats for scripting:
orfyn ls --json # JSON output
orfyn ls --format yaml # YAML output
orfyn ls -q # IDs only (quiet)
Global options
--host <target>, connect to a different daemon (host:port, unix socket, orhttps://app.orfyn.in/#offer=...for relay). See Connecting to a remote daemon.--json, JSON output-q, --quiet, minimal output--no-color, disable colors