Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.linksee.app/llms.txt

Use this file to discover all available pages before exploring further.

Your persistent memory across all AI tools. When the user says “use linksee” or asks about past decisions, context, or preferences, call this first. Returns memories ranked by a composite score of relevance, heat, momentum, and importance.

​
Parameters

​
query
string
required
What you want to remember. Free-text, entity name, or FTS5 MATCH expression.
​
entity_name
string
Narrow results to a specific entity.
​
layer
string
Filter by memory layer. Accepts aliases (e.g. warnings → caveat).
​
altitude
string
Filter by cognitive altitude: mission, strategy, architecture, implementation.
​
mem_type
string
Filter by memory type: question, comparison, decision, work, outcome, learning, note.
​
mem_state
string
Filter by lifecycle state: open, decided, in_progress, done, stalled, parked, superseded.
​
thread_id
string
Filter by thread ID — returns all memories in a decision chain or session group.
​
band
string
Filter by heat band: hot, warm, cold, frozen.
​
max_tokens
number
default:"2000"
Approximate token budget. Iteration stops when this budget is consumed or limit is reached, whichever comes first.
​
limit
number
Hard cap on number of memories returned.
​
offset
number
default:"0"
Skip this many top results (pagination). Use has_more from prior response to decide next offset.
​
mark_accessed
boolean
default:"true"
Set false for preview / listing queries that should not bump heat scores.

​
Ranking

Memories are ranked by a composite score: 
score = 0.45 * relevance + 0.25 * heat + 0.15 * momentum + 0.15 * importance
FactorWeightSource
Relevance45%FTS5 BM25 score + LIKE match
Heat25%Ebbinghaus decay since last access
Momentum15%Entity activity frequency
Importance15%User-assigned or auto-inferred

​
Response

Each memory in the response includes:
  • match_reasons — array explaining why this memory ranked (e.g. content_match_fts, entity_name_match, heat:hot, pinned, caveat_protected)
  • score_breakdown — individual scores for transparency
  • has_more — boolean indicating if more results exist beyond the current page
  • stopped_by — whether iteration stopped at tokens, limit, or end

​
Example

{
  "query": "Supabase connection pooling",
  "layer": "caveat",
  "max_tokens": 3000
}
Dual search: Recall uses both FTS5 full-text search (BM25-ranked, trigram tokenizer) and LIKE fallback, merging and deduplicating results. This ensures both exact and fuzzy matches are found, including Japanese text.