Skip to main content
Glama

memorry

memorry banner

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.

Related MCP server: tartarus-mcp

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/İi, şs, ğg, üu, öo, çc) 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

A
license - permissive license
-
quality - not tested
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
1Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    A local, fully-offline MCP memory server that enables persistent storage and retrieval of information using SQLite with both keyword and semantic vector search capabilities.
    10
    13
    12
    MIT
  • A
    license
    -
    quality
    D
    maintenance
    A local-first MCP memory server providing persistent, searchable memory for AI agents, powered by SQLite.
    1
    1
    Apache 2.0
  • A
    license
    -
    quality
    D
    maintenance
    A local-first MCP server providing persistent, searchable knowledge base via SQLite, enabling AI agents to save and recall facts across sessions without cloud dependencies.
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    A local-first MCP server for durable agent memory using SQLite and FTS5, enabling knowledge graph storage, search, and recall for AI agents.
    20
    1
    MIT

View all related MCP servers

Related MCP Connectors

  • User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.

  • Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.

  • Person-owned, portable AI memory as a remote MCP server, readable and writable by any MCP client.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/macbyclp/memorry'

If you have feedback or need assistance with the MCP directory API, please join our Discord server