Enrichment is a set of 📝Augmentation controls that make a MythOS library legible to AI agents — link suggestions that surface as you write, a write-time link lint that keeps the knowledge graph connected when agents write, one-line memo descriptions agents scan before opening anything, and a health check for semantic search. It exists because agents drafting at speed skip the linking step a careful human takes: they save memos naming people, companies, and concepts the library already holds without linking a single one, and every unlinked write quietly starves the graph, backlinks, and retrieval. Enrichment is for creators who work with AI agents inside their library — especially over the MythOS MCP — and want every write to strengthen the corpus instead of fragmenting it.

Key Capabilities

• Link suggestions as you write — in a memo or the Journal, titles your library recognizes get a subtle dotted underline; hover for a one-click Insert, or dismiss it for that document. An Enrich All button at the top of the memo adds every pending suggestion at once, after confirming how many memos it will link — each linked once, at its first occurrence. Collaborators editing a memo get suggestions too, drawn from their own library. Always a suggestion, never a block.
• Write-time link lint — every memo write is checked for known titles it names without linking; off, suggest (default), or require.
• Require mode for agents — agent writes introducing unlinked references are rejected until linked or explicitly acknowledged; human edits are never blocked.
• You choose which names your agents must link — every memo title is a name your agents are asked to link by default; there is no automatic everyday-word filter. You curate the exceptions in Settings → Enrichment: set a memo to Never enrich, or mute a whole tag, so a word like work is not required, and set Always enrich to force a name.
• Choose what gets suggested — set which memos count (minimum length, tag and mention requirements), which visibilities can be suggested inside which, whether suggestions appear at every mention or only the first in memos and in your daily memo, and whether titles from libraries you manage or communities you steward are offered.
• Auto-generate descriptions — turn on Auto-generate for new memos and descriptions are written on your Anthropic key as you create memos, with existing memos filled in gradually in the background.
• Aliases and opt-outs — alternate names a memo is recognized by, plus a per-memo opt-out that removes a memo from recognition entirely.
• AI memo descriptions — one-line agent-facing summaries generated with Claude Haiku on your own Anthropic key, cost-estimated before anything runs.
• Semantic search health — see how much of your library is indexed for search and chat, and reindex whatever is missing or out of date.

Getting Started

Everything manages from one settings page: Settings → Enrichment (/settings/enrichment).

1. Choose how strictly your AI agents must link the memos they mention — Off, Suggest (default), or Require.
1. Before switching to Require, review which names are required. Under Customize enrichments, search for any memo whose name would be noise and set it to Never enrich, mute whole tags that should never be required, and set Always enrich on names you always want linked. It takes one pass, and after it Require is safe to leave on.
1. Write normally — type-time suggestions are on by default, so recognized titles get a dotted underline in memos and the Journal; hover one and click Insert to turn the mention into a link.
1. Add an Anthropic API key under Settings → AI, then generate descriptions across your qualifying memos — the estimated cost shows before anything runs.
1. Tune any single memo — edit its description, add the other names it goes by, or change whether its name is required.
1. Check search coverage and reindex whatever is missing or out of date, with the cost shown first.

FAQ

• What does require mode actually block? Only agent and API writes that introduce a new unlinked reference to a known memo. Pre-existing unlinked names are reported but never block, and human edits in the editor always stay suggestion-only.
• Won't Require reject everything, if I have memos named after common words? It can, until you curate. Every memo title is enforced by default, so mark everyday-word titles Never enrich (or mute their tags) before turning Require on; after that, a rejection means the agent skipped a reference you chose to require.
• Can an agent override a rejection? For a missing link, yes — deliberately. The rejection lists the unlinked memos, and the agent either rewrites the content with @mentions or retries while acknowledging specific memo IDs. Forgetting cannot produce an override; only an explicit act can.
• Is there anything an agent cannot override? Yes, and it is the important exception. If a write would expose a private memo — a public memo mentioning one that isn't public — that is a privacy boundary, not a linking suggestion. It cannot be acknowledged away at any setting, and it is blocked even when the writer has no access to the memo in question. The only fix is to remove the mention.
• What do descriptions cost? They run on your own Anthropic key, never platform billing — fractions of a cent per memo. A 12,000-memo library filtered to roughly 7,000 qualifying memos runs about $10, and the dashboard shows the estimate before you confirm.
• Will regeneration overwrite a description I wrote by hand? No. Hand-edited descriptions are never touched by the bulk pass. The only way to replace one is the per-memo Regenerate button, which asks first.
• Which memos qualify? By default, memos with at least 200 characters of content and at least one tag or link; you can change the length floor and the tag and mention requirements under What gets suggested. The same rule governs suggestions, lint matching, and description generation, so short stubs never create noise or generation cost. Qualifying is not the same as being required, though: whether a memo is substantial enough to deserve links and whether its name is safe to enforce are separate questions, which is why a long, well-written memo named work still gets a description and still gets suggested, but never blocks a write.
• How are suggestions ranked when more than one memo could match? By how closely your words match a memo's name, highest weight first. A looser match is tried only when nothing closer matches, so a variation never outranks an exact name.

1. 1. Exact name and case — a title or "also known as" name spelled exactly as written, capitalization included. Always on. When several memos share that exact name, the primary-tag rule below can choose between them.
   1. Capitalization — the same name in different upper and lower case. On by default.
   1. Accents & spacing — accent marks and extra spaces between words ignored. Off by default.
   1. Possessives — a trailing ’s still counts as the name. Off by default.
   1. Hyphens & punctuation — hyphens, dashes and dots count as spaces. Off by default.
   1. Plurals — singular and plural of the name's last word count as the same. Off by default.

• • Names match whole words only, so a memo named "Git" never matches inside the word "GitHub". When one memo's full name contains another's — say your library has memos named "New York" and "New York Times" — typing "New York Times" suggests that memo, not "New York", even though both are exact matches. Typing "New York" on its own suggests "New York".
  • When several memos tie at the closest match, you choose. With Use primary tag to choose on, the one whose 📝primary tag is also on the memo you're writing is chosen for you; if none or several fit, you still choose. A tie is never linked by Enrich All.

Related

• 📝Semantic Search — the embedding layer whose health the Enrichment page reports
• 📝BYOK — the key setup that description generation runs on
• 📝Mentions & Backlinks — the linking the lint protects

Contexts

• 🏷️#mythos
• 🏷️#mythos-feature
• 🏷️#mythos-ai-augmentation