CLI Reference

Commands

Command	Description
`initrunner run <role.yaml>`	Run an agent (single-shot or interactive)
`initrunner validate <role.yaml>`	Validate a role definition
`initrunner init`	Scaffold a template role, tool module, or skill
`initrunner setup`	Guided setup wizard (provider selection + test)
`initrunner ingest <role.yaml>`	Ingest documents into vector store
`initrunner daemon <role.yaml>`	Run in trigger-driven daemon mode
`initrunner serve <role.yaml>`	Serve agent as an OpenAI-compatible API
`initrunner test <role.yaml> -s <suite>`	Run a test suite against an agent
`initrunner pipeline <pipeline.yaml>`	Run a pipeline of agents
`initrunner tui`	Launch TUI dashboard
`initrunner ui`	Launch web dashboard (requires `[dashboard]` extra)
`initrunner install <source>`	Install a role from GitHub or community index
`initrunner uninstall <name>`	Remove an installed role
`initrunner search <query>`	Search the community role index
`initrunner info <source>`	Inspect a role's metadata without installing
`initrunner list`	List installed roles
`initrunner update [name]`	Update installed role(s) to latest version
`initrunner plugins`	List discovered tool plugins
`initrunner audit prune`	Prune old audit records
`initrunner audit export`	Export audit records as JSON or CSV
`initrunner memory clear <role.yaml>`	Clear agent memory store
`initrunner memory export <role.yaml>`	Export memories to JSON
`initrunner skill validate <path>`	Validate a skill definition
`initrunner skill list`	List available skills
`initrunner compose up <compose.yaml>`	Run compose orchestration (foreground)
`initrunner compose validate <compose.yaml>`	Validate a compose definition
`initrunner compose install <compose.yaml>`	Install systemd user unit
`initrunner compose uninstall <name>`	Remove systemd unit
`initrunner compose start <name>`	Start systemd service
`initrunner compose stop <name>`	Stop systemd service
`initrunner compose restart <name>`	Restart systemd service
`initrunner compose status <name>`	Show systemd service status
`initrunner compose logs <name>`	Show journald logs
`initrunner compose events <compose.yaml>`	Stream compose orchestration events
`initrunner create <description>`	Generate a role YAML from a natural-language description using AI
`initrunner examples list`	List available example roles
`initrunner examples clone <name>`	Clone an example role to the current directory
`initrunner examples info <name>`	Show details about an example role
`initrunner mcp introspect <role.yaml>`	List tools exposed by MCP servers in a role
`initrunner --version`	Print version

Run Options

Flag	Description
`-p, --prompt TEXT`	Single prompt to send
`-i, --interactive`	Interactive REPL mode
`--resume`	Resume the previous REPL session (requires `memory:` config)
`--dry-run`	Simulate with TestModel (no API calls)
`--audit-db PATH`	Custom audit database path
`--no-audit`	Disable audit logging
`-a, --autonomous`	Run without user confirmation for tool calls
`--max-iterations INT`	Maximum autonomous iterations
`--skill-dir PATH`	Additional directory to load skills from

Combine flags: initrunner run role.yaml -p "Hello!" -i sends a prompt then continues interactively.

Init Options

Flag	Description
`--name TEXT`	Agent name (default: `my-agent`)
`--template TEXT`	Template: `basic`, `rag`, `daemon`, `memory`, `ollama`, `tool`, `api`, `skill`
`--provider TEXT`	Model provider (default: `openai`)
`--output PATH`	Output file path (default: `role.yaml`)

Serve Options

Flag	Description
`--host TEXT`	Host to bind to (default: `127.0.0.1`)
`--port INT`	Port to listen on (default: `8000`)
`--api-key TEXT`	API key for Bearer token authentication
`--audit-db PATH`	Custom audit database path
`--no-audit`	Disable audit logging
`--cors-origin TEXT`	Allowed CORS origin (repeatable)
`--skill-dir PATH`	Additional directory to load skills from

See API Server for endpoint details, streaming, and usage examples.

Daemon Options

Flag	Description
`--skill-dir PATH`	Additional directory to load skills from

Compose Subcommands

Subcommand	Description
`compose up <file>`	Start orchestration in foreground
`compose validate <file>`	Validate compose definition
`compose install <file>`	Install systemd user unit
`compose uninstall <name>`	Remove systemd unit
`compose start <name>`	Start systemd service
`compose stop <name>`	Stop systemd service
`compose restart <name>`	Restart systemd service
`compose status <name>`	Show service status
`compose logs <name>`	Show journald logs (`-f` to follow, `-n` for line count)
`compose events <file>`	Stream compose orchestration events

See Compose for full multi-agent orchestration documentation.