Ingest
Ingest a document or URL into Kagura Memory — extract text, chunk it, and store an overview plus per-section memories. Use when the user wants to add a PDF, Office/HTML/EPUB file, audio/video, or a web page to their memory graph.From its SKILL.md
npx -y skills add kagura-ai/kagura-memory-python-sdk --skill ingestAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.4 KB, as published. Nobody here has run it
kagura ingest — document ingestion
Drive kagura ingest to turn a file or URL into a structured set of memories.
Thin wrapper around the installed kagura CLI.
Preflight
kagura --version; if missing →uv tool install kagura-memory(orpip install kagura-memory), then stop.- Heavy parsers are opt-in extras (e.g.
pip install 'kagura-memory[ingest-pdf]'or[ingest-all]); a missing parser surfaces a clear "install ..." error from the CLI — relay that hint rather than guessing. - Requires authentication and a target context. Run
kagura auth status; if not authed, run theauthskill first.
Run
kagura ingest ./report.pdf # local file
kagura ingest https://example.com/page # URL
kagura ingest ./report.pdf --dry-run # preview cost/sections; no LLM or backend write
kagura ingest ./report.pdf --json # machine-readable result for scripting
Consume the result
- Relay the overview + per-section counts and any per-section error records.
- On a missing-extra error, surface the exact
pip installcommand the CLI prints. Use--dry-runfirst when the user wants a cost/size estimate.