{"slug":"michielinksee/linksee-memory","name":"Linksee Memory","description":"Local-first cross-agent memory MCP. 6-layer structured brain (goal/context/emotion/impl/caveat/learning) with token-saving file diff cache (86% measured savings on re-reads)","category":"productivity","tags":[],"official":false,"stars":11,"transport":"stdio","install":[{"cmd":"npx -y linksee-memory","imports":[]}],"tools":[{"name":"remember","description":"Store memory in 1 of 6 layers for an entity. Rejects pasted assistant output / CI logs unless `force=true`. Set `importance=1.0` to pin (survives auto-forget)."},{"name":"recall","description":"FTS5 + heat × momentum × importance composite ranking with `match_reasons` explaining WHY each row matched. Supports pagination (`offset`/`has_more`), `band` filter, layer aliases (`decisions`/`warnings`/`how`/...), and `mark_accessed=false` for passive previews."},{"name":"recall_file","description":"Complete edit history of a file across all sessions, with per-edit user-intent context. **v0.3.0** `scope_to_roots` flag filters by client roots."},{"name":"update_memory","description":"**v0.1.0** Atomic edit of an existing memory. Preserves `memory_id` (session_file_edits links stay intact). Prefer over forget+remember."},{"name":"list_entities","description":"**v0.1.0** List what the memory knows about — cheapest \"what do I know?\" primitive. Filter by `kind`/`min_memories`; returns layer breakdown per entity."},{"name":"read_smart","description":"Diff-only file read. Returns full content on first read, ~50 tokens on unchanged re-reads, only changed chunks on real edits."},{"name":"forget","description":"Explicit delete OR auto-sweep based on `forgettingRisk`. Pinned (`importance>=1.0`) and caveat-layer memories are always preserved. **v0.3.0** `interactive` flag asks the user via Elicitation before deleting a specific memory_id."},{"name":"consolidate","description":"Sleep-mode compression: cluster cold low-importance memories → protected learning-layer summary. Supports `dry_run` preview. **v0.3.0** `use_llm` flag asks the client LLM (Sampling) to rewrite cluster summaries into prose."}],"env_vars":[],"auth_type":"none","github":"https://github.com/michielinksee/linksee-memory","homepage":"","server_url":"","status":"active","source":"mcpservers.org","updated_at":"Thu May 28"}