lore_forget
Soft-delete one or more memories by ID.
LABSCO SUMMARY
The store improves because the agent rates what it used.
Most memory tools only get bigger; here retrieval quality is a function of feedback, so a store that has been used for months surfaces different things from a fresh one. Two habits make that work: call the update tool after acting on a memory rather than only reading it, and end sessions with a reflection so discoveries and lessons enter the store as memories instead of dying with the transcript. Link suggestions are deliberately advisory — nothing is written into the graph until you accept it.
What it is
A local memory store for agents. Memories go into SQLite with vectors alongside, and search is hybrid — semantic plus keyword, weighted by recency, how often a memory gets used, and the score feedback has given it.
What you get
- A single thought captured in one call, for the moments when stopping to structure something would mean not writing it down at all
- Hybrid search over the store with a minimum score, a date window, a source-type filter and a sort, or a straight bulk fetch by id when you already know what you want
- Feedback written back after a memory is used, which is the loop that raises useful memories and lets weak ones decay out
- Memories and links inserted together, with near-identical content refused unless you force it through
- Link candidates between a memory and its neighbours, ranked with per-signal scores — suggested only, never written until you confirm
- A queue of pending link suggestions sorted by quality, accepted or rejected in bulk
- Session reflection: a completed session summarised into what was done, the decisions taken, factual discoveries, lessons learnt and good patterns, with the resulting memories inserted
- The session ids already reflected on, so the same session is not processed twice
- Soft deletion of memories by id with a reason recorded, rather than a hard erase
Requirements
No account, no key, no cloud: pip install lorekeeper-mcp, then lorekeeper setup and lorekeeper. Setup detects the agents installed on the machine and writes the MCP entry, the agent prompt and the bundled skills for each — --check previews it without writing. Storage is SQLite plus LanceDB on your own disk, so the store is a local file you back up yourself, and namespaces are what let several agents share one store while writing into their own space. A separate dashboard command opens a web UI for browsing, editing and backup. Apache-2.0.
Setup effort
One command — pip install lorekeeper-mcp && lorekeeper setup && lorekeeper
USE CASES
01
Not re-explaining the codebase every session
Store the fact once — the middleware path, the token lifetime, the command you prefer — and search brings it back in the next session on any connected agent.
02
Turning a finished session into something reusable
Reflect on the session with what was done, the decisions, the discoveries and the lessons; the pieces become searchable memories rather than scrollback.
03
Making retrieval sharper over time
Rate the memories and links after using them; useful ones surface more often and unused, low-confidence ones fade out of results.
04
Building a graph without hand-linking everything
Ask for ranked link candidates around a memory, review the pending suggestions by quality, and accept or reject them in one go.
05
Correcting something the store learned wrong
Soft-delete the memories by id with the reason recorded, and insert the corrected version in their place.
10 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
lore_get_suggestions
Retrieve pending link suggestions for review, sorted by quality score.
lore_insert
Insert memories and/or links into the store.
lore_processed_sessions
Return all session IDs that have been marked as processed via lore_reflect.
lore_recommend_links
Suggest link candidates between a memory and related memories. Returns ranked candidates with per-signal scores. Does NOT write any links — call lore_insert with links=[] to confirm.
lore_reflect
Reflect on a completed session — save what you learned.
lore_remember
Capture a thought instantly — one fact, one call.
lore_review_suggestion
Accept or reject one or more link suggestions in a single call.
lore_search
Search memories by semantic + keyword query, or bulk-fetch by ID.
When `ids is provided, skips the vector/BM25 pipeline entirely and does a direct SQL lookup by lore_id. query` is ignored in that path.
lore_update
Rate memories and links after using them. Drives the quality signal loop.
BEFORE YOU INSTALL
What to know first
Tools you get
10 tools when we connected.
CONTEXT COST
Light Standing cost
Rated by the size of the 10 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install lorekeeper-mcp && lorekeeper setup && lorekeeper
