MemoGraph 🧠

MemoGraph turns a folder of markdown notes into a queryable, AI-ready knowledge graph. It solves the LLM memory problem — your AI assistants forget last Tuesday's decision, can't find a related note across two projects, and re-derive the same insight again and again — by giving them a persistent, navigable, attribution-friendly memory layer that lives in plain markdown files you control.

You write notes the way you already do. MemoGraph indexes them, builds a graph from [[wikilinks]], ranks them by salience, and serves them back to your LLM (or your team) on demand.

⚡ Try it in 60 seconds

pip install memograph
memograph quickstart

That's it. The quickstart command drops a small, interconnected sample vault on your disk (15 notes about Python development, with real wikilinks between them), ingests it, and runs three live demo queries so you can see the graph + hybrid retrieval working before you decide whether to commit. Try this query in particular:

memograph --vault ~/memograph-quickstart search "FastAPI dependency injection"

The vault contains a note titled FastAPI dependencies (about Depends(...)) — the words "dependency" and "injection" never appear in any note's title. MemoGraph still finds it, because hybrid retrieval understands "dependency injection" semantically and the wikilink graph stitches related notes together. That's the product, demonstrated in one query.

Re-run memograph quickstart --force any time to reset to a fresh demo. When you're ready, point MemoGraph at your real notes: memograph --vault ~/your-notes ingest.

What you get

As a solo user / knowledge worker

• A vault of human-readable markdown files — nothing proprietary, no lock-in. Your notes outlive any tool.
• Hybrid retrieval that combines keyword search, semantic similarity, and graph traversal so you find the right note even when you don't remember the exact words.
• AI-assisted tagging, link suggestions, and gap detection that grow your knowledge base instead of letting it rot.
• A CLI and a web UI for browsing, editing, and visualizing the graph.

As an AI agent / IDE user

• A first-class Model Context Protocol (MCP) server with 30+ tools, working out of the box with Claude Desktop, Claude Code, Cursor, Cline, Windsurf, Continue, Zed, VS Code, Goose, Gemini CLI, OpenAI Codex CLI, and others.
• Autonomous "auto-save" hooks that capture decisions and context from your AI conversations into the vault automatically.
• Per-conversation memory recall — your assistant can pull "what did we decide last week about X" without you copy-pasting context every time.

As an enterprise / SaaS operator

• Multi-tenant deployment with filesystem-level isolation per tenant, end-to-end isolation tests, and a warm-LRU kernel cache.
• OIDC + API-key authentication with JWKS support (Auth0, Clerk, WorkOS, Keycloak, Azure AD, Okta), restrictive CORS, request-size caps, and rate limiting.
• GDPR-compliant scheduled deletion: tombstone-with-grace-period flow, automatic final backups, daily reaper, and an audit log of every deletion.
• Observability built in: OpenTelemetry traces + Prometheus /metrics, structured JSON logging with request IDs, and a separate /healthz / /readyz for orchestration.
• Operations runbooks shipped with the code: install, SSO setup, RBAC, backup-restore, and GDPR procedures.

How consumers benefit

✨ Capabilities at a glance

Core memory engine

• Graph-based memory — bidirectional [[wikilinks]] build a navigable knowledge graph automatically.
• Hybrid retrieval — keyword + semantic embeddings + graph traversal, combined and re-ranked.
• Memory types inspired by cognitive science: episodic, semantic, procedural, fact.
• Salience scoring (0–1) that decays over time and boosts on access.
• Smart indexing — mtime-cached, only re-parses changed files.
• Context compression — token-budget-aware windowing for LLM prompts.
• Markdown-native vault — every memory is a .md file with YAML frontmatter; no proprietary format.

AI features

• Smart Auto-Organization Engine — extract topics, people, action items, decisions, questions, sentiment, risks, ideas, and timeline events from memories.
• AutoTagger — suggest tags via semantic analysis, structure detection, and pattern learning.
• LinkSuggester — propose [[wikilinks]] to related notes; bidirectional opportunities included.
• GapDetector — surface missing topics, weak coverage, isolated notes, and unmade links.
• Knowledge analysis — vault stats, topic clustering, learning paths, connection analysis.

Interfaces

• Python API — MemoryKernel with sync, async, and batch variants.
• CLI — 24+ commands for ingest, search, batch ops, import, export, backup, and AI features.
• MCP server — 30+ tools, stdio transport, drop-in for any MCP-compatible client.
• Web UI — React + D3 graph visualization, search, and editing (FastAPI backend + Vite frontend).
• HTTP API — versioned /api/v1/, OpenAPI snapshot in CI, ready for service-to-service integration.

Enterprise & SaaS readiness

• Multi-tenancy with filesystem-isolated tenants, an LRU registry of warm kernels, per-tenant audit logs, and end-to-end isolation tests gating release.
• Authentication via OIDC (JWKS) or hashed API keys; per-route auth scope; identity bound into the audit log.
• Web hardening — restrictive CORS, slowapi rate limiting, request-size caps, structured JSON logging with request IDs, info-leak-free 500 handler.
• Storage hardening — path-traversal-safe vault writes, vault size soft/hard caps, schema-versioned cache files.
• Scheduled deletion for GDPR Art. 17: tombstone with configurable grace period, automatic final backup, daily reaper script, cancel-before-grace endpoint.
• Observability — OpenTelemetry FastAPI/asyncio auto-instrumentation, Prometheus /metrics, OTLP export.
• Reliability — concurrency audit, stress tests for concurrent writes, versioned backup format with integrity checks.
• Distribution — pinned-and-locked dependencies, Docker compose for self-host, security workflow (bandit + pip-audit).

See docs/INSTALL_ENTERPRISE.md, docs/SSO_SETUP.md, docs/GDPR_RUNBOOK.md, docs/BACKUP_RESTORE_RUNBOOK.md, docs/OBSERVABILITY_GUIDE.md, and docs/RBAC_GUIDE.md for the operator-facing details.

🚀 Quick Start

Hosting it yourself? docs/HOSTING_GUIDE.md covers four genuinely-free paths — Oracle Free Tier, Cloudflare Tunnel + your hardware (recommended for most), GCP always-free stitch, and GitHub-repo-as-vault. Workspace identity via OIDC and Drive-as-portability-backup are documented in docs/GOOGLE_WORKSPACE_SETUP.md.

Installation

pip install memograph

Install with optional dependencies:

# For OpenAI support
pip install memograph[openai]

# For Anthropic Claude support
pip install memograph[anthropic]

# For Ollama support
pip install memograph[ollama]

# For embedding support
pip install memograph[embeddings]

# Install everything
pip install memograph[all]

Python Usage

from memograph import MemoryKernel, MemoryType

# Initialize the kernel attached to your vault path
kernel = MemoryKernel("~/my-vault")

# Ingest all notes in the vault
stats = kernel.ingest()
print(f"Indexed {stats['indexed']} memories.")

# Programmatically add a new memory
kernel.remember(
    title="Meeting Note",
    content="Decided to use BFS graph traversal for retrieval.",
    memory_type=MemoryType.EPISODIC,
    tags=["design", "retrieval"]
)

# Retrieve context for an LLM query
context = kernel.context_window(
    query="how does retrieval work?",
    tags=["retrieval"],
    depth=2,
    top_k=8
)

print(context)

🔌 MCP Server (Model Context Protocol)

MemoGraph includes a full-featured MCP server for seamless integration with AI assistants like Cline and Claude Desktop.

📖 New to MemoGraph MCP? See the MCP User Guide for practical usage instructions and examples!

🚨 Having connection issues? See Setup & Troubleshooting Guide - Common fixes for "cannot connect" errors!

19 Available Tools

Supported Clients

MemoGraph's MCP server is a stdio server — it runs alongside any MCP-compatible agentic CLI or editor. The full setup cookbook (config-file paths, format quirks, verification steps) lives in docs/MCP_CLIENTS.md:

Launching the MCP server

After pip install memograph (or uv tool install memograph), three launch commands are all equivalent:

memograph-mcp                              # console script (recommended)
python -m memograph.mcp.run_server         # module form (works with any Python)
uvx --from memograph memograph-mcp         # zero-install via uv

memograph-mcp and memograph are both registered as console scripts: the first starts the MCP server, the second is the CLI. They do not collide.

Read-only mode

For shared deployments or untrusted clients, set MEMOGRAPH_READONLY=true. The server refuses every vault-writing tool — create_memory, import_document, update_memory, delete_memory, relate_memories, bulk_create, batch_update, batch_delete, import_backup_tool, and the auto-save hooks — and returns a structured {"success": false, "readonly": true, "error": "..."} payload instead. Read tools (search_vault, query_with_context, list_memories, get_memory, analytics, graph traversal) stay fully functional.

Quick Setup for Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "memograph": {
      "command": "memograph-mcp",
      "env": {
        "MEMOGRAPH_VAULT": "/path/to/your/vault"
      }
    }
  }
}

If the memograph-mcp binary isn't on the client's PATH (common when the client launches without your shell environment), use the explicit module form instead:

{
  "mcpServers": {
    "memograph": {
      "command": "python",
      "args": ["-m", "memograph.mcp.run_server"],
      "env": {
        "MEMOGRAPH_VAULT": "/path/to/your/vault"
      }
    }
  }
}

Quick Setup for Cline

Add to your ~/.cline/mcp_settings.json:

{
  "mcp": {
    "servers": {
      "memograph": {
        "command": "memograph-mcp",
        "env": {
          "MEMOGRAPH_VAULT": "/path/to/your/vault"
        }
      }
    }
  }
}

For Claude Code, Cursor, Windsurf, Continue, Zed, VS Code, Goose, Gemini CLI, Codex CLI, LM Studio, Cherry Studio, and Bob Shell, see docs/MCP_CLIENTS.md.

Install from MCP Registry

NEW: MemoGraph is now available in the official MCP Registry! 🎉

Registry URL: https://github.com/modelcontextprotocol/servers/tree/main/src/memograph

pip install memograph

Then drop the snippet for your client into its config file (see the table above or docs/MCP_CLIENTS.md).

Benefits of MCP Registry Listing:

• ✅ Official registry backed by Anthropic, GitHub, and Microsoft
• ✅ Discoverable by all MCP-compatible clients
• ✅ Verified server card and metadata
• ✅ Direct link from PyPI package
• ✅ Trusted by the MCP community

Note: The registry uses the PyPI package version. When you pip install memograph, you automatically get the latest registry-listed version.

See MCP_REGISTRY_GUIDE.md for complete submission and configuration guide.

Usage Examples

Once configured, use natural language with your AI assistant:

"Search my vault for memories about Python"
"Create a memory titled 'Project Ideas' with content '...'"
"Update memory abc-123 to have salience 0.9"
"Delete memory xyz-456"
"What tools are available?"
"Get vault statistics"

See CONFIG_REFERENCE.md for complete MCP configuration guide.

Using Auto-Save Hooks

MemoGraph provides autonomous hooks to save conversations automatically:

• ⚠️ Important: Hooks are passive tools - see Autonomous Hooks Guide for setup
• 📝 Quick fix: Add custom instructions to Claude Desktop (instructions in guide)
• 🔧 Configure with MEMOGRAPH_AUTONOMOUS_MODE=true

Read the full Autonomous Hooks User Guide →

🎯 CLI Usage

MemoGraph comes with a powerful CLI for managing your vault and chatting with it.

Ingest

Index your markdown files into the graph database:

memograph --vault ~/my-vault ingest

Force re-indexing all files:

memograph --vault ~/my-vault ingest --force

Remember

Quickly add a memory from the command line:

memograph --vault ~/my-vault remember \
    --title "Team Sync" \
    --content "Discussed Q3 goals." \
    --tags planning q3

Context Window

Generate context for a query:

memograph --vault ~/my-vault context \
    --query "What did we decide about the database?" \
    --tags architecture \
    --depth 2 \
    --top-k 5

Ask (Interactive Chat)

Start an interactive chat session with your vault context:

memograph --vault ~/my-vault ask --chat --provider ollama --model llama3

Or ask a single question:

memograph --vault ~/my-vault ask \
    --query "Summarize our design decisions" \
    --provider claude \
    --model claude-3-5-sonnet-20240620

Diagnostics

Check your environment and connection to LLM providers:

memograph --vault ~/my-vault doctor

### Import Documents

Import documents (TXT, PDF, DOCX) and convert them to markdown:

```bash
# Import a single file
memograph --vault ~/my-vault import document.pdf --type episodic

# Import entire folder
memograph --vault ~/my-vault import ~/Documents --recursive

# Preview files without importing (dry run)
memograph --vault ~/my-vault import ~/Documents --dry-run

# Auto-ingest after import
memograph --vault ~/my-vault import document.pdf --auto-ingest

Batch Operations

Efficiently manage multiple memories at once:

# Bulk create memories from JSON/CSV
memograph --vault ~/my-vault batch-create memories.json

# Bulk update memories by filter
memograph --vault ~/my-vault batch-update \
    --filter-tags outdated \
    --add-tags reviewed \
    --salience 0.8

# Bulk delete with safety checks
memograph --vault ~/my-vault batch-delete \
    --filter-type episodic \
    --filter-max-salience 0.3 \
    --dry-run

Data Management

Export, backup, and restore your vault:

# Export vault to JSON/CSV/Markdown
memograph --vault ~/my-vault export --format json --output backup.json

# Create timestamped backup
memograph --vault ~/my-vault backup --output ./backups

# Restore from backup
memograph --vault ~/my-vault import-backup backup.zip

Configuration & Statistics

Manage settings and view vault analytics:

# View vault statistics
memograph --vault ~/my-vault stats

# Configure settings
memograph config set embedding_provider openai
memograph config get embedding_provider
memograph config list

# Manage profiles
memograph config profile create work --vault ~/work-vault
memograph config profile use work

MCP Setup

Interactive wizard to configure MCP server for Claude Desktop or Cline:

# Run interactive setup wizard
memograph setup-mcp

# Verify MCP configuration
memograph verify-mcp

📖 Complete CLI Documentation: See CLI Usage Guide for detailed documentation with 200+ examples covering all 24 commands.

🤖 AI Features

MemoGraph includes powerful AI-powered features to enhance your knowledge management workflow. See AI Features Guide for complete documentation.

🏷️ AutoTagger - Intelligent Tag Suggestions

Automatically suggest relevant tags using semantic analysis, content structure, and existing patterns:

# Suggest tags for a note
memograph suggest-tags note.md

# Apply high-confidence suggestions automatically
memograph suggest-tags note.md --apply

# Adjust confidence threshold and limit
memograph suggest-tags note.md --min-confidence 0.5 --max-suggestions 10

Features: Frequency-based extraction • Semantic similarity • Structure detection • Pattern learning • Confidence scoring

🔗 LinkSuggester - Smart Wikilink Recommendations

Intelligently recommend wikilinks to related notes using semantic similarity and graph analysis:

# Suggest links for a note
memograph suggest-links note.md

# Apply suggestions automatically
memograph suggest-links note.md --apply

# Show bidirectional link opportunities
memograph suggest-links note.md --show-bidirectional

Features: Semantic search • Keyword matching • Graph-based suggestions • Bidirectional detection • Target previews

🔍 GapDetector - Knowledge Base Analysis

Identify missing topics, weak coverage, and isolated notes in your vault:

# Detect all gaps
memograph detect-gaps

# Focus on high-severity gaps
memograph detect-gaps --min-severity 0.7

# Export results to JSON
memograph detect-gaps --output json > gaps.json

Gap Types: Missing Topics • Weak Coverage • Isolated Notes • Missing Links

📊 Knowledge Analysis - Comprehensive Insights

Get comprehensive analysis of your entire knowledge base:

# Full analysis with all features
memograph analyze-knowledge

# Export detailed report to JSON
memograph analyze-knowledge --output json > analysis.json

Analysis Includes: Vault statistics • Topic clustering • Learning paths • Gap detection • Connection analysis

Python API for AI Features

from memograph import MemoryKernel
from memograph.ai import AutoTagger, LinkSuggester, GapDetector

kernel = MemoryKernel("~/my-vault")
kernel.ingest()

# Get tag suggestions
tagger = AutoTagger(kernel, min_confidence=0.4)
suggestions = await tagger.suggest_tags(
    content="Python is great for data science",
    title="Data Science with Python"
)

# Get link suggestions
suggester = LinkSuggester(kernel, min_confidence=0.5)
links = await suggester.suggest_links(
    content="Python async programming tutorial",
    title="Async Python"
)

# Detect knowledge gaps
detector = GapDetector(kernel, min_severity=0.5)
gaps = await detector.detect_gaps()

# Comprehensive analysis
analysis = await detector.analyze_knowledge_base()

📖 Complete Documentation:

• AI Features Guide - Comprehensive guide with examples
• Web UI Guide - Using AI features in the browser
• MCP AI Tools Guide - AI features for Claude & Cline

💡 Use Cases: Auto-organize notes • Discover connections • Identify gaps • Maintain consistency • Build learning paths

📖 Core Concepts

Memory Types

MemoGraph supports different types of memories inspired by cognitive science:

• Episodic: Personal experiences and events (e.g., meeting notes)
• Semantic: Facts and general knowledge (e.g., documentation)
• Procedural: How-to knowledge and processes (e.g., tutorials)
• Fact: Discrete factual information (e.g., configuration values)

Graph Traversal

The library uses BFS (Breadth-First Search) to traverse your knowledge graph:

# Retrieve nodes with depth=2 (2 hops from seed nodes)
nodes = kernel.retrieve_nodes(
    query="graph algorithms",
    depth=2,  # Traverse up to 2 levels deep
    top_k=10  # Return top 10 relevant memories
)

Salience Scoring

Each memory has a salience score (0.0-1.0) that represents its importance:

---
title: "Critical Architecture Decision"
salience: 0.9
memory_type: semantic
---

We decided to use PostgreSQL for better ACID guarantees...

🏗️ Project Structure

MemoGraph/
├── memograph/          # Main package
│   ├── core/           # Core functionality
│   │   ├── kernel.py   # Memory kernel
│   │   ├── graph.py    # Graph implementation
│   │   ├── retriever.py # Hybrid retrieval
│   │   ├── indexer.py  # File indexing
│   │   └── parser.py   # Markdown parsing
│   ├── adapters/       # LLM and embedding adapters
│   │   ├── embeddings/ # Embedding providers
│   │   ├── frameworks/ # Framework integrations
│   │   └── llm/        # LLM providers
│   ├── storage/        # Storage and caching
│   ├── mcp/            # MCP server implementation
│   └── cli.py          # CLI implementation
├── tests/              # Test suite
├── examples/           # Example usage
└── scripts/            # Utility scripts

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

Development Setup

1. Clone the repository:

   bash

   git clone https://github.com/Indhar01/MemoGraph.git
   cd MemoGraph
   

2. Install in development mode:

   bash

   pip install -e ".[all,dev]"
   

3. Install pre-commit hooks:

   bash

   pre-commit install
   

4. Run tests:

   bash

   pytest
   

Code Quality

We maintain high code quality standards:

• Linting: Ruff for fast Python linting
• Formatting: Ruff formatter for consistent code style
• Type Checking: MyPy for static type analysis
• Testing: Pytest with comprehensive test coverage
• Pre-commit Hooks: Automated checks before each commit

📚 Documentation

Getting Started

• Hosting Guide - 💸 Free hosting options (Oracle Free Tier, Cloudflare Tunnel, GCP, GitHub-vault) with hardening checklist
• Google Workspace Setup - 🔐 OIDC identity + Drive portability backup
• MCP Clients Guide - 🔌 Setup snippets for 15+ agentic CLIs/editors (Claude Code, Cursor, Windsurf, Continue, Zed, VS Code, Goose, Gemini CLI, Codex CLI, LM Studio, …)
• MCP User Guide - ⭐ Start here! Complete guide for using MemoGraph MCP
• Setup & Troubleshooting - 🚨 Can't connect? Step-by-step fixes for connection issues
• MCP Testing Guide - Testing your MCP server after setup

For Developers & Contributors

• MCP Registry Guide - Publishing to official MCP Registry
• Versioning Strategy - Semantic versioning and release planning
• AGENTS.md - Guide for AI agents working with this codebase
• Contributing Guide - How to contribute to the project
• Code of Conduct - Community guidelines
• Security Policy - Security reporting and best practices
• Changelog - Version history and changes

🔒 Security

See our Security Policy for reporting vulnerabilities.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🌟 Acknowledgments

Inspired by the need for better memory management in LLM applications. Built with:

• Graph-based knowledge representation
• Hybrid retrieval strategies
• Cognitive science principles

📬 Contact & Support

• Issues: GitHub Issues
• Discussions: GitHub Discussions

📣 Community & Feedback

We value community feedback and contributions! Here's how to get involved:

Report Issues

Found a bug or have a feature request? Open an issue on GitHub.

Discussions

Join the conversation in GitHub Discussions:

• Ask questions
• Share use cases
• Suggest improvements
• Show what you've built

Contributing

We welcome contributions! See our Contributing Guide for details on:

• Code contributions
• Documentation improvements
• Bug reports and feature requests
• Community support

Stay Updated

• ⭐ Star the repository on GitHub
• 👁️ Watch for updates and releases
• 📦 Follow the project on PyPI
• 🔗 Check out the MCP Registry listing

🚦 Status

Current version: 0.3.0

Single-tenant deployments are stable and recommended for production use. Multi-tenant deployments are feature-complete with end-to-end isolation tests gating the release; the public API will stabilise at v1.0.

• ✅ Core functionality stable and tested (172+ tests across security, contract, and tenancy suites)
• ✅ Whole-package type-checked with MyPy
• ✅ Ruff lint + format + pre-commit hooks
• ✅ OpenAPI v1 contract snapshot in CI
• ✅ Multi-tenant isolation invariants verified by an e2e test suite
• ⚠️ Public API may change in minor versions until v1.0.0

What landed recently

• Phase 3.7 — GDPR-compliant scheduled tenant deletion: tombstone-with-grace-period, daily reaper, automatic final backups.
• Phase 3.5 — TenantRegistry wired into the request path; non-admin routes resolve their kernel per-tenant.
• Phase 3 scaffold — multi-tenancy ADR, TenantStorage, TenantRegistry, admin routes for tenant lifecycle.
• Phase 2 — OpenTelemetry + Prometheus, structured JSON logging, concurrency audit, stress tests.
• Phase 1 — OIDC + API-key auth, slowapi rate limiting, restrictive CORS, request-size caps, vault size caps, schema-versioned caches, OpenAPI v1 contract, security test suite.
• Phase 0 — path-traversal-safe vault writes, info-leak-free error handlers, pinned dependencies, Docker compose, security CI workflow.
• 📦 Published to the official MCP Registry (io.github.indhar01/memograph)

Made with ❤️ for better LLM memory management