bibi

Summarize videos, audio, and podcasts directly from the terminal using BibiGPT. Run scripts/bibi-check.sh first. It detects which mode is available: If neither mode is available, see references/installation.md for setup instructions. Route the user's request to the appropriate workflow: The bibi CLI directly accepts local file paths (no upload needed): For API mode (no CLI), guide the user to upload the file to a publicly accessible URL (OSS, S3, etc.) first, then pass that URL to the API. See references/supported-platforms.md for details. Use progressive help to discover options: bibi --help → bibi summarize --help → run. For simple, single-command requests that don't need a full workflow: See references/cli.md for all commands and flags. - Supports YouTube, Bilibili, podcasts, and other media URLs with multiple output formats: Markdown, JSON, raw subtitles, or chapter-by-chapter breakdowns - Requires BibiGPT desktop app with active login or BIBI_API_TOKEN environment variable for authentication - Includes async mode for long videos (>30 min) to avoid timeouts, plus commands for checking auth status, managing tokens, and self-updating - Output streams to stdout (summaries) and stderr (progress), enabling piping to files or tools like jq for structured data extraction - If the user's intent matches more than one workflow, ask one clarifying question before routing.