memorry

A fully local, API-key-free MCP memory server for Claude Code (or any MCP client). No Ollama, no embeddings, no external LLM calls — just SQLite, FTS5 full-text search, and optional live sync to an Obsidian vault.

Built collaboratively with Claude Code (Anthropic).

Why

Most "AI memory" setups either ship your notes to a hosted vector DB or require a local embedding model. memorry doesn't do either. It's a single Python process exposing a handful of MCP tools backed by one SQLite file. The calling agent is responsible for distilling what's worth remembering into one self-contained sentence — the server just stores it verbatim and makes it searchable.

Features

• Local-first: one SQLite file (memory.db), streamable-http on 127.0.0.1:8765, no network calls of any kind.
• FTS5 full-text search with Turkish/English stopword filtering and Turkish character folding (ı/İ→i, ş→s, ğ→g, ü→u, ö→o, ç→c) so search is forgiving of accents and common function words.
• Projects: every record is tagged with a project, so one server can hold memory for several unrelated things.
• Pinned records: mark a handful of memories as always-relevant; fetch them without a search query.
• Live Obsidian sync: every add/update/delete mirrors to one or more Obsidian vault folders as Markdown notes with frontmatter, and each new note auto-links to the most relevant existing notes in the same project via [[wikilink]] — so the vault's Graph View reflects real semantic connections, no manual linking required.
• Automatic backups: a timestamped copy of the DB is taken on every server start (last 30 kept).
• Health check: memory_health runs an actual write test against the FTS5 index, not just PRAGMA integrity_check — see a real bug we hit below.
• Export/import: dump to JSON, re-import elsewhere with automatic dedup.

Tools

Tool	Purpose
memory_add(text, project, pinned)	Store a fact verbatim
memory_search(query, project, limit)	FTS5 search, bm25-ranked
memory_list(project, limit, pinned_only)	List recent (or pinned) records
memory_update(id, text, project, pinned)	Edit in place, id/created_at preserved
memory_delete(id)	Remove a record
memory_stats()	Record counts, per-project breakdown, DB size
memory_health()	Integrity check + a real FTS5 write test
memory_export(project)	Dump to JSON
memory_import(path)	Re-import a JSON dump, deduped

Use with Claude Code

Two optional pieces ship with the server, and they do different jobs:

SKILL.md — the discipline. Search before you add, distill to one self-contained sentence, separate projects, when to reach for memory_health. Claude loads it on its own whenever memory is relevant, so you don't have to ask for it.

mkdir -p ~/.claude/skills/memorry
cp SKILL.md ~/.claude/skills/memorry/

commands/hatirla.md — the shortcut. A slash command for when you want to bank something right now without breaking your train of thought: /hatirla the deploy key rotates every 90 days. ("hatırla" is Turkish for "remember" — rename the file to change the command name.)

mkdir -p ~/.claude/commands
cp commands/hatirla.md ~/.claude/commands/

Both land in ~/.claude/, so they work from any project. Drop them in a project's own .claude/ instead if you'd rather scope them to one repo. The command file has a "customize this" note at the bottom — worth two minutes to point it at your own project names.

Setup

pip install -r requirements.txt
python server.py

Or on Windows, run start-memory.bat to launch it hidden in the background (no autostart — you start it when you want it running).

Then point your MCP client at http://127.0.0.1:8765/mcp. For MCP hosts that only support command/args-style stdio servers (some desktop clients don't speak native type: http yet), bridge it with mcp-remote:

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "http://127.0.0.1:8765/mcp", "--allow-http", "--transport", "http-only"]
    }
  }
}

Obsidian sync

Edit OBSIDIAN_DIRS in server.py to point at one or more vault subfolders. Leave the list empty (or point it somewhere that doesn't exist) to skip Obsidian entirely — it's best-effort and never blocks a memory write if the vault folder is unreachable.

Design notes

• The agent distills, the server doesn't. memory_add never summarizes or calls out to an LLM — it stores exactly what it's given. Tool descriptions instruct the calling agent to compress information into one self-contained sentence before writing, and to search first so duplicate/stale facts don't pile up.
• Turkish-aware, not Turkish-only. The stopword list and character folding cover Turkish because that's what this was built for, but everything degrades gracefully for English text.

A real bug we hit

While building this, memories_fts was originally an FTS5 "external content" table (content='memories', content_rowid='id'). At some point its shadow tables got corrupted in a way PRAGMA integrity_check and even FTS5's own integrity-check command both reported as fine — but any DELETE/INSERT against the index raised database disk image is malformed. The underlying memories table was untouched.

The fix was to drop the external-content linkage entirely: memories_fts is now a fully independent FTS5 table, rebuilt from memories on every server start (cheap at personal-notes scale). memory_health() exists specifically to catch this class of failure early — it does a real (harmless, rowid=-999999) write against the index rather than trusting integrity_check alone.

License

MIT