Collecting is not the finish line

Most people do not fail to save things. They save too widely: a chat log, a bookmark folder, a download directory, and one conclusion nobody can find again.

LLM-notebook does one job — it puts four kinds of material in one place, and makes each of them askable the moment it lands.

Four sources, four entry points

• LLM chats: hit "Save chat" on ChatGPT, Claude, DeepSeek and friends. The whole thread is filed with its platform label attached. No copy-paste.
• Web links: paste a URL. Title, body and images are fetched and parsed into a searchable item.
• Files: PDF, Word, PPT, Markdown, images. Drop them in and they are parsed and filed.
• Agent sessions: with the skill installed, tell your agent "save this to LLM-notebook" and the session becomes a note.

Four doors, one room. After that you stop caring which app it came from.

Filing is the hard part

Saving is one click. Filing decides whether you can still find it three months later. So parsing extracts title, source, time and body structure up front, and every item carries those dimensions from birth.

Found is what makes it collected. Unfindable is just a copy.

Three things worth doing

1. Add one line of your own when you save it. You will thank yourself in three months.
2. Layer with folders, not tags. Keep tags for cross-topic keywords.
3. Ask a question right after saving — that turns a stored item into a used one.

Install the browser extension or the skill and all of this happens inside the workflow you already have.