Skip to content

CLI Usage

ankurCES edited this page Jun 4, 2026 · 6 revisions

CLI Usage

Run blumi <command> --help for the full flags of any subcommand.

blumi [--provider P] [--model M] [--persona NAME] [--sandbox local|docker] [COMMAND]

With no command on a TTY, blumi launches the TUI.

Core

Command Description
blumi / blumi tui Interactive terminal UI
blumi run "<prompt>" Run one prompt headlessly, streaming to stdout (pipeable)
blumi login Setup wizard: provider, key/endpoint, model
blumi web Embedded React web UI + HTTP/SSE server
blumi serve … Always-on gateway for the phone app → Gateway
echo "summarize this diff" | blumi run -          # read prompt from stdin
git diff | blumi run "review these changes" --yolo
blumi --persona reviewer run "audit src/auth.rs"

TUI essentials

  • enter send · / command palette · ^p palette · tab focus · esc nav
  • ^b toggle rails · ^y YOLO (auto-approve) · ^c quit
  • Slash: /help /model /persona /theme /memory /usage /tasks /yolo /compact /undo /sessions /new /resume /quit

Task board + autonomous loop

blumi task add "write tests for parser" -p 1     # add a task (priority 1=highest)
blumi task list                                  # show the board
blumi loop --max 5 --yolo                        # work the board: select → run → advance

The loop pulls the highest-priority todo, runs it as a turn, and advances it. Bound it with --max <n> and --budget <usd>; --review sends finished tasks to review instead of done. On a grid it can hand tasks off to peers.

Management & automation

Command Description
blumi session List / search / show stored sessions (FTS5 full-text search)
blumi stats Aggregate token usage across sessions
blumi cron Schedule prompts on a timer
blumi playbook <file.yaml> Run a multi-step workflow with gates + resume
blumi skills Manage the bundled SKILL.md library + your own → Self-Management
blumi mcp Manage MCP servers (defaults + a catalog)
blumi gateway Run as a messaging bot (Telegram/Discord/Slack/WhatsApp)

Global flags

  • --provider / --model — override the LLM for this run.
  • --persona — start with a named persona.
  • --sandbox local|docker — run tools on the host or in a container (needs the docker feature).

Clone this wiki locally