Lore

Persistent, queryable memory for AI coding assistants. Lore runs entirely on your machine and stores design decisions, rejected approaches, and coding patterns in a local Qdrant vector database, then surfaces them to Claude Code (or any MCP-compatible AI) before it proposes changes so it never re-suggests what you've already ruled out.

How it works

Lore exposes five MCP tools over stdio:

Tool	What it does
memory_search	Retrieve relevant memories before proposing a design
memory_record	Store a new decision, rejection, pattern, or note
memory_list_recent	Browse recently stored memories
memory_forget	Delete a memory by ID
memory_supersede	Replace an outdated memory with a new one

Memories are embedded with Ollama (nomic-embed-text) for dense vectors and BM25 for sparse vectors. Queries use hybrid retrieval (RRF fusion) with a recency boost — so recent decisions are ranked higher.

System prompt

Add prompts/system-addition.md to your editor's instructions/rules file. This tells the AI to call memory_search before designing and memory_record when decisions are made.

Session auto-capture (optional)

Automatically extract memories from completed Claude Code sessions. Requires ANTHROPIC_API_KEY.

Add to ~/.claude/settings.json:

{
  "hooks": {
    "Stop": [{
      "matcher": "",
      "hooks": [{ "type": "command", "command": "/abs/path/to/hooks/session-end.sh" }]
    }]
  }
}

Architecture

lore add / memory_record
  └─ scrub secrets
  └─ dense embed (Ollama) + sparse embed (BM25)
  └─ Qdrant UpsertWithSparse

lore search / memory_search
  └─ embed query
  └─ Qdrant hybrid search (RRF fusion) + recency boost
  └─ return top-k

lore ingest-session <transcript>
  └─ parse JSONL → scrub → chunk
  └─ Anthropic extracts memories as JSON
  └─ cosine dedup gate → upsert

Qdrant stores named vectors: dense (768-d cosine) + sparse (BM25). Repo identity is stable across renames: git.RepoID uses SHA256 of the remote origin URL when available.