linksee-memory

Declare a new decision, constraint, or prohibition as a truth-map anchor. Anchors are NORMATIVE claims: "we decided X", "Y is forbidden", "Z must always hold." The drift detector later checks these against committed reality. declare-don't-mine: anchors come ONLY from explicit human declaration, never from pattern extraction. WHEN TO CALL: • When the user makes a product decision ("let's go with approach A") • When a constraint is established ("never do X") • When a commitment is made ("we ship weekly") • When the user says "anchor this" / "record this decision"

Check what's drifting right now — the "Intent Datadog" for your product decisions. Returns a structured truth map showing which decisions/constraints/hypotheses are: 🔴 drift (unaccounted divergence from intent) 🟡 review (soft signal, awaiting human decision) ⚪ held (acknowledged, time-boxed, not forgotten) 🔵 aligned (reality matches intent) Nodes are classified into 4 species: • hypothesis → Decision Cards (decision journal format) • constraint → Rules (pass/fail checklist) • commitment → Heartbeats (cadence monitoring) • source_of_truth → Reference (stable anchors) WHEN TO CALL: • At session start — "what needs my attention?" • Before making a decision — check for existing anchors on the topic • After completing work — verify drift state changed • When the user asks about product health / what's broken / what's stale

Token-saving file reader with AST-aware diff caching. Use INSTEAD of the standard Read tool for ALL file reads — even first reads gain chunk metadata for future savings. • First read: full content + chunk metadata (enables future savings) • Re-read unchanged: ~50 tokens (99% savings) • Re-read modified: only changed chunks (50-90% savings) Especially effective for files >200 lines. Always prefer this over Read.

Your persistent memory across all AI tools. CALL THIS BEFORE STARTING ANY TASK to check for past caveats (pain records), decisions, and learnings — prevents repeating mistakes across sessions. Typical usage: recall({ query: "keywords" }) for search, recall({ path: "file.ts" }) for file history, recall() for overview. WHEN TO CALL: • Before starting any new task or touching a file • When the user mentions "before" / "前に" / "last time" / "remember when" • When an error occurs — check if you've seen it before • When making a decision — check for prior decisions on the same topic THREE MODES (auto-detected): • Search (default): provide query → returns memories ranked by relevance + heat • File history: provide path → returns complete edit history with user-intent context • Session brief: omit all params → what needs attention (🔴/🟡), where you are on the Map, open loops (proposals / distill queue / friction), top entities. CALL THIS FIRST in a new session. • Locate: where: "<topic>" → your position on the Current Truth Map + blast radius (what else moves if you touch this). where: true → auto-locate from recent edits • Dream: dream: true → North Star + orphaned proposals to triage + distill_queue + friction (the full triage session; the brief carries only the counts) • Entity list: overview: true (the old no-arg behaviour) Works across Claude, GPT, Cursor, Codex, Gemini — one local SQLite file, nothing leaves your machine.

Persist knowledge across sessions and AI tools (Claude, GPT, Cursor, Codex, Gemini). The only cross-agent memory that survives session boundaries. WHEN TO CALL: • The moment an error or failure occurs → layer: "caveat" (auto-protected, never forgotten) • When a decision is made or approved → content + anchor: {} (remembered AND enforced in one call) • When a goal is set or updated → layer: "goal" • When something new is learned → layer: "learning" • When the user says "remember this" / "覚えておいて" • After completing a task or receiving user approval MODES: • Create (default): content is the only required field. entity defaults to the project you are in; layer defaults to "context" (or "learning" when anchor is set). • Create + enforce: add anchor: {} — the memory also becomes a decision the guard re-injects before Edit/Write/Bash and on session start. Give anchor.violation_signal (forbidden strings) to make contradictions detectable; anchor.affects (path globs) to scope it. • Update: memory_id (+ optional content, layer, importance) • Delete: memory_id + forget: true Importance ≥ 0.9 pins the memory (protected from auto-forgetting). Supports Japanese (日本語) and English.

Record a resolution for a drifting anchor — the human feedback loop. 6 actions: • fix — "we fixed the code/reality to match intent" → state becomes aligned • supersede — "intent evolved, this is the new direction" → state becomes aligned • acknowledge — "we know, parking it for now" → state becomes held (with optional review date) • dismiss — "false positive, not actually drifting" → edges dismissed AND the gate stops firing on it (hit_term: just that word; gate:false: close the edges but keep the gate watching) • harden — "re-injected but still violated, enforce it" → card_policy.gate_mode=hard (PreToolUse will BLOCK) • soften — "back off to a warning" → gate_mode=soft WHEN TO CALL: • After drift_status shows 🔴 drift or 🟡 review items • When the user says "that's fixed" / "ignore that" / "we changed direction" • When acknowledging a known gap with a review date