
Memory Fts
Adds persistent memory to Claude Code with hybrid search combining SQLite FTS5 and semantic embeddings. Exposes five tools: memory_save to store facts with categories like preference or technical, memory_search for BM25 plus vector similarity merged via RRF, memory_update, memory_list, and memory_delete. The hook setup automatically injects your top 30 memories into every prompt based on access frequency and recency decay. Embeddings run locally with all-MiniLM-L6-v2, so nothing leaves your machine. Reach for this when you want Claude to remember project decisions, your coding preferences, or technical context across sessions without manual copy-paste.
- tools
- 5
- transport
- STDIO
- env var
- 1
- last updated
- Mar 13, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
memory_saveSave a fact to long-term memory.
Save a fact to long-term memory.
No parameter schema in public metadata yet.
memory_searchHybrid search: runs FTS5 and semantic search in parallel, merges results with RRF. Falls back to LIKE for partial matches.
Hybrid search: runs FTS5 and semantic search in parallel, merges results with RRF. Falls back to LIKE for partial matches.
No parameter schema in public metadata yet.
memory_updateUpdate a memory's content or category by ID.
Update a memory's content or category by ID.
No parameter schema in public metadata yet.
memory_listList all saved memories grouped by category.
List all saved memories grouped by category.
No parameter schema in public metadata yet.
memory_deleteDelete a memory by ID.
Delete a memory by ID.
No parameter schema in public metadata yet.
Sponsors
Configuration
MEMORY_DB_PATHCustom path to the SQLite database file (default: ~/.claude/memory.db)
Readme
claude-memory-fts
Long-term memory MCP server for Claude Code. Stores facts in a local SQLite database with hybrid search (FTS5 + semantic vector similarity) and automatic context injection.
Features
- Hybrid search — FTS5 keyword search + semantic vector similarity, merged via Reciprocal Rank Fusion (RRF)
- Semantic understanding — find memories by meaning, not just keywords (powered by all-MiniLM-L6-v2 embeddings)
- Auto context injection — top 30 most important memories injected into every prompt via hook
- Importance ranking — facts ranked by access frequency, recency decay, and category weight
- Access tracking — tracks how often each memory is accessed
- Upsert — automatically updates existing facts instead of duplicating
- Categorized — organize by type: preference, decision, technical, project, workflow, personal, general
- MCP Resources — exposes
memory://contextresource for session context - Zero config — works out of the box, stores data in
~/.claude/memory.db
Install
# Add to Claude Code
claude mcp add memory -- npx claude-memory-fts
Details
- Repository
- github.com/kurovu146/claude-memory-mcp
- Categories
- Databases, AI & LLM Tools, Search & Web Crawling
- Package
claude-memory-fts- Transport
- STDIO
- Registry
- MCP registry, active