MCP SERVERA local memory an agent keeps across sessions and across tools, plus a map of your declared decisions that flags when the code has drifted from them.
LABSCO SUMMARY
Anchors are declared by a human rather than inferred from logs, and the drift check reconciles them against reality afterwards — which is what keeps the map from filling up with things nobody actually agreed. Caveat-layer entries, the 'never do this again' records, are the ones shielded from auto-forgetting, so the hard-won mistakes outlive everything else in the store.
One SQLite file on your machine that Claude Code, Cursor, Windsurf, Codex and Gemini CLI can all read from — structured memory with ranked recall, and a truth map of decisions the drift detector checks against committed reality.
Nothing to authorize and nothing leaves the machine: memory lives in ~/.linksee-memory/memory.db, relocatable with LINKSEE_MEMORY_DIR. npx -y linksee-memory setup does the whole install — registers the stdio server, installs the agent skill that teaches the agent when to recall and remember, wires a Stop hook that captures each session, and offers to add the re-injection guard to the project's .claude/settings.json. By hand instead: claude mcp add -s user linksee -- npx -y linksee-memory. Any client that speaks stdio can connect with the same command.
One command — npx -y linksee-memory setup
USE CASES
Recall the caveats attached to this area before starting, and write the new one down the moment something breaks.
Declare it as an anchor with its rationale, then open it later to see whether reality still agrees.
Read the map of diverging anchors, then record what you decided to do about each one.
Locate the topic on the map and read the blast radius around it.
Flag the orphaned proposals, weigh them against the project's direction, then keep or drop each one.
Read through the caching reader so unchanged files come back as a diff rather than in full.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
check_decisionDeep-dive into a specific decision/anchor — its state, premises, drift edges, and pending candidates.
Returns the full context for one truth-map node: what was decided, why, what reality says, whether it's drifting, and what actions are pending.
WHEN TO CALL:
declare_anchorDeclare 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:
dreamReturns the project's North Star alongside the unresolved proposals flagged during conversations, for the evaluating agent to surface or dismiss.
drift_statusCheck 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:
WHEN TO CALL:
flag_proposalsRecord orphaned proposals — options you presented that the user never addressed.
Conversations are tree-shaped but experienced linearly. When you present 3 options and the user engages with only 1, the other 2 become "orphaned proposals" — unresolved decision branches that both you and the user lose track of.
WHEN TO CALL:
read_smartToken-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.
Especially effective for files >200 lines. Always prefer this over Read.
recallRetrieves stored caveats, decisions and learnings by search query, by file path, or as an overview when called with no arguments.
rememberStores knowledge that survives session boundaries, filed into a layer such as caveat, learning or goal and tied to an entity or thread.
resolve_driftRecord a resolution for a drifting anchor — the human feedback loop.
6 actions:
WHEN TO CALL:
resolve_proposalRecord your evaluation verdict for an orphaned proposal after dreaming.
Call this after dream for each candidate you evaluated against the North Star.
Always reference the North Star criteria in your rationale.
where_am_iLocate the current topic on the Current Truth Map and report "you are here" + blast radius — the per-turn re-anchor.
Returns the matching Map node(s) + journey stage (discover → … → expand), the BLAST RADIUS (what becomes suspect if you change this — the must-stay-consistent-with / should-align-with / realizes dependents; e.g. editing the README implicates the LP), and the decision behind the node (linked anchor), if any.
Three ways to call:
This is how you avoid optimizing one node while silently breaking its neighbors (change the spec → npm/Docs/LP must move too). Matching is lexical (no embeddings).
WHEN TO CALL:
BEFORE YOU INSTALL
11 tools when we connected.
npx on PATH
All 5 documented clients run the server on your machine.
CONTEXT COST
Rated by the size of the 11 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
npx -y linksee-memory setupclaude mcp add -s user linksee -- npx -y linksee-memory{
"mcpServers": {
"linksee": {
"command": "npx",
"args": [
"-y",
"linksee-memory"
]
}
}
}[mcp_servers.linksee]
command = "npx"
args = ["-y", "linksee-memory"]MCP servers
GuyMannDude
omega-memory
oleksiijko
nikitacometa