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.

Save important context that should persist across sessions and across AI tools. When the user says “use linksee”, “remember this”, “don’t forget”, or you discover a decision, preference, or lesson worth preserving — store it here. Memories saved here are accessible from any AI agent the user connects to — Claude, GPT, Cursor, Codex, Gemini.

​
Parameters

​
entity_name
string
required
Name of the entity this memory is about (e.g. “MyProject”, “Supabase”, “Alice”).
​
entity_kind
string
required
One of: person, company, project, concept, file, other.
​
layer
string
required
Memory layer. One of: goal, context, emotion, implementation, caveat, learning.Common aliases are accepted:
AliasResolves to
why, intent, targetsgoal
background, reason, timingcontext
tone, feelings, moodemotion
impl, how, triedimplementation
warning, pain, pitfall, dontcaveat
decision, insight, growthlearning
​
content
string
required
The memory content. Plain text or JSON.
​
importance
number
0.0 to 1.0. Set to 0.9 or higher to pin a memory — pinned memories are protected from auto-forgetting even outside the caveat layer. Default: auto-assigned based on layer.
​
thread_id
string
Optional thread ID to group related memories (e.g. a session ID or decision chain). Enables decision → implementation → outcome tracing.
​
force
boolean
default:"false"
Bypass the paste-back quality check. Set true only when you are sure the content is original user or agent thought, not pasted CI logs or assistant output.

​
Example

{
  "entity_name": "KanseiLink",
  "entity_kind": "project",
  "layer": "caveat",
  "content": "Never deploy freee OAuth changes on Friday — their sandbox goes down for maintenance every Friday night JST.",
  "importance": 0.95
}

​
Behavior

  1. Entity resolution: 3-tier matching — canonical_key exact → normalized_name → case-insensitive name → insert new entity
  2. Quality check: Rejects pasted CI logs, assistant output, and other non-original content (bypass with force: true)
  3. Auto-structuring: Plain text is wrapped into structured JSON with inferred altitude, type, and state classifications
  4. Pinning: Memories with importance >= 0.9 get protected = 1, preventing auto-forgetting
  5. Events: Records a memory_stored event for momentum tracking
Caveat-layer memories are always protected regardless of importance score. They survive consolidation and auto-forgetting indefinitely.