AI Diary MCP Server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
✨ Highlights
🔒 Truly private. Every memory lives in one SQLite file on your disk. Nothing is ever uploaded.
🧠 No embeddings, still smart. Retrieval uses SQLite FTS5 + BM25 with a trigram tokenizer, so search is instant and works great for English and 中文 / CJK.
🤝 Borrows your platform's brain. When the host supports MCP sampling,
recallexpands & re-ranks andreflectauto-summarizes — with graceful fallback when it doesn't. The server itself never ships a model.🕸️ A real knowledge graph. Link memories and traverse the web of context.
🗂️ Collections, tags, importance, reflection, dedup. Organize like Notion — locally and programmatically.
🎨 A beautiful local dashboard. Browse, search, and add memories in your browser (dark & light).
🧩 Works everywhere MCP does. Claude Desktop, Cursor, Windsurf, Cline, VS Code, Zed…
Related MCP server: genmem
🖥️ The dashboard
A polished local web UI over the same database — npm run dashboard, then open http://localhost:4178.
Browse · full-text search (English + 中文) · filter by tag/collection · spot near-duplicates · add memories · dark/light theme · one-click git snapshot.
🏆 Why it's better than Notion
AI Diary | Notion | |
Privacy | 100% local, single file you own | Cloud-hosted |
Built for AI | Native MCP tools an agent calls directly | Manual / limited API |
Chinese search | FTS5 trigram — precise CJK substring search | Weak |
Knowledge graph | First-class links + graph traversal | No |
Offline | Always | No |
Cost | Free, no subscription | Paid tiers |
Versioning | Optional git history of your memory | Limited |
🚀 Quick start
git clone https://github.com/pangxianggang/ai-diary-mcp.git
cd ai-diary-mcp
npm install
npm run build # produces dist/index.js — the stdio MCP server
npm run smoke # self-test (26 assertions)Try the dashboard with some sample data:
AI_DIARY_DB_PATH=./demo.db node scripts/seed-demo.mjs
AI_DIARY_DB_PATH=./demo.db npm run dashboard # http://localhost:4178Override the port with
AI_DIARY_PORT.
🎨 The design philosophy
The server is the hippocampus — fast storage, structure, and retrieval. Your platform's model is the cortex — it reasons, summarizes, and decides what to remember.
The server never calls an LLM and never goes online. That keeps it private, free, and trivially portable.
💾 Where memories are stored
A single SQLite file:
OS | Default path |
Windows |
|
macOS |
|
Linux |
|
Override with AI_DIARY_DB_PATH. Back up by copying the file. Keep it inside a git repo and call snapshot for versioned memory history.
🔌 Connect it to your AI
Use the absolute path to the built dist/index.js.
Claude Desktop
claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": {
"ai-diary": {
"command": "node",
"args": ["/absolute/path/to/ai-diary-mcp/dist/index.js"]
}
}
}Cursor / Windsurf / Cline / Zed / VS Code
All use the same shape — command: "node" with args pointing at dist/index.js. Add an env block to relocate the database:
{
"mcpServers": {
"ai-diary": {
"command": "node",
"args": ["/absolute/path/to/ai-diary-mcp/dist/index.js"],
"env": { "AI_DIARY_DB_PATH": "/absolute/path/to/my-memory.db" }
}
}
}Restart the client after editing its config.
🧰 Tools
Tool | What it does |
| Save a memory ( |
| Search by text (FTS5 BM25, CJK-aware) with optional |
| List the most recently created memories. |
| Browse chronologically by when things occurred. |
| Fetch one memory by id, including its links. |
| Edit an existing memory. |
| Archive (default) or hard-delete a memory. |
| Connect two memories into a knowledge graph (e.g. |
| Traverse the knowledge graph around a memory (BFS to a depth) and return connected memories + links. |
| Surface near-duplicate memories via trigram similarity. |
| Group memories into Notion-like collections. |
| All tags with usage counts. |
| Totals, categories, time range, db location. |
| Export memories as Markdown. |
| Consolidate related memories. |
| Commit the SQLite file to git for versioned memory history. |
Resource memory://recent (recent entries as Markdown) · Prompt recall-about (recall + summarize a topic).
🧱 Capabilities by phase
MVP — SQLite + FTS5 (CJK trigram) + full CRUD over stdio, one-line client config.
Smart retrieval — optional MCP-sampling query expansion + re-ranking in
recall, automatic fallback to plain FTS5.Structure — tags, collections, links / knowledge graph traversal, importance, soft-forget.
Reflection —
reflect auto=trueconsolidates memories via the host model;find_duplicatesfor de-duplication.Experience — a polished local web dashboard + Markdown export + optional git-versioned history.
🔍 How search works (without embeddings)
FTS5 + BM25 ranks entries by relevance. The trigram tokenizer indexes 3-character sequences, which is what makes substring and CJK search work.
Metadata filters (tags, category, collection, time range, importance) narrow results.
Queries shorter than 3 characters fall back to a
LIKEsubstring scan.With
smart=true, a sampling-capable host expands the query and re-ranks candidates — but the core works fully without it.
🛠️ Development
npm run dev # tsc --watch
npm run typecheck # type-check only
npm run smoke # in-memory end-to-end check (26 assertions)
npm run dashboard # local web UI📄 License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
Persistent, portable memory for AI assistants — your private memory graph, from any MCP client.
Persistent, verbatim, searchable memory for AI assistants — one memory across every MCP client.
Cloud-hosted MCP server for durable AI memory
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA local-first MCP server for personal memory management, enabling AI agents to store, search, and retrieve developer insights with offline semantic search and auto-categorization.24 npm3MIT
- AlicenseNot gradedqualityCmaintenanceA local-first MCP server that gives AI assistants long-term memory by storing, searching, and recalling notes as Markdown files on your machine.9 npmMIT
- AlicenseNot gradedqualityCmaintenanceA self-hostable MCP server that provides permanent memory for AI agents using Postgres + pgvector for semantic search and Markdown file sync.2 npmMIT
- AlicenseAqualityBmaintenanceA fully local MCP server that gives AI agents persistent, semantic long-term memory without any cloud dependencies.11123 npm2MIT