mcp-memory-graph
About
Persistent memory for AI agents using a semantic knowledge graph. Store, retrieve, and connect memories with semantic search — so your AI remembers context across sessions.
Details
- Author
- retrorobai
- Categories
- AI, Knowledge Base, Other
Jump to
Setup
Install mcp-memory-graph in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/retrorobai/mcp-memory-graph
Follow the installation instructions in the repository README, then restart your MCP client.
A context-aware memory MCP server for Claude Code and any MCP-compatible AI agent.
Goes beyond basic vector search by addingauthority weighting,conflict detection, andtyped relationship edgesbetween memories — so your agent always retrieves the right answer when sources disagree.
Inspired by the context engine architecture described inUnblocked's "How a Context Engine Actually Works".
Standard memory MCP servers store and retrieve memories by semantic similarity. That works until you have conflicting memories — an old instruction saying one thing and a new one saying another. Without authority weighting, the agent retrieves whichever is semantically closer to the query, not whichever is more trustworthy.
mcp-memory-graphsolves this with three mechanisms:
git clone https://github.com/RetroRobAI/mcp-memory-graph cd mcp-memory-graph pip install -r requirements.txt python server.py
Add to~/.claude.jsonundermcpServers:
"mcp-memory-graph": { "type": "stdio", "command": "mcp-memory-graph", "env": { "MEMORY_GRAPH_DB_PATH": "/path/to/memories.db" } }
"mcp-memory-graph": { "type": "stdio", "command": "python", "args": ["/path/to/mcp-memory-graph/server.py"], "env": { "MEMORY_GRAPH_DB_PATH": "/path/to/memories.db" } }
Migrating from an existing memory service
If you have an existing memory service (mcp-memory-service, Mem0, or a markdown-based memory system), you can import your memories into mcp-memory-graph using the included migration script.
Migration is manual and opt-in— it never runs automatically. Nothing is written until you explicitly confirm.
- Auto-detect any existingmcp-memory-serviceSQLite database
- Ask if you have a markdown memory directory to import
- Show you how many memories it found
- Present three choices:
- [1] Migrate— import everything into mcp-memory-graph
- [2] Run in parallel— start mcp-memory-graph fresh, keep your old service running
- [3] Skip— do nothing
Your existing memory service is never modified — the script only reads from it.
priority="high" # authority_score=1.0 — explicit instructions, confirmed preferences priority="medium" # authority_score=0.6 — inferred preferences, reference data priority="low" # authority_score=0.3 — session summaries, historical context
Retrieval ranking:weighted_score = 1 - (distance / (authority_score + 0.001) / 10)
A high-authority memory will rank above a semantically closer low-authority one when their similarity scores are within ~3x of each other.
- supersedes— this memory replaces another
- relates_to— connected but not conflicting
- contradicts— explicitly conflicting, unresolved
- referenced_by— another memory cites this one
- sqlite-vec— vector similarity search
- sentence-transformers— local embeddings, no API key needed
- FastMCP— MCP server framework
Adaptive MCP memory system for AI applications. Learns which retrieval strategies work for your data, scores results using cognitive science models, builds a knowledge graph automatically, and validates every parameter change against real query history before adopting it. Patent pending.
Self-hosted Rust-based MCP server for AI agent memory — persistent, queryable memory with hybrid search, knowledge graphs, built-in embeddings, and 14 core tools (expandable to 86+ with profile-based tiering).
Self-improving MCP memory server for AI agents. One command, no cloud, no config. Hybrid search, feedback loop quality system, dashboard UI, auto-linking knowledge graph. Gets better the more you use it.
🏠 🍎 🪟 🐧 - A self-contained Memory server with single-binary architecture (embedded DB & models, no dependencies). Provides persistent semantic and graph-based memory for AI agents.
Smriti is a Model Context Protocol (MCP) server that provides persistent, graph-based memory for LLM applications. Built on LadybugDB (embedded property graph database), it uses EcphoryRAG-inspired multi-stage retrieval - combining cue extraction, graph traversal, vector similarity, and multi-hop association - to deliver human-like memory recall.
MCP-native memory layer for Claude Code, Cursor, Cline, Continue, and 16 other AI tools. Hybrid search (BM25 + pgvector + graph), self-hosted on Supabase + Vercel, 100% MIT, no paywall.
Highly efficient context management for agentic AI: MCP code search, evidence packs, graph context, and memory for large projects.
Self-hosted MCP server giving AI agents persistent memory — Markdown source of truth, hybrid BM25+embedding search, typed graph relations.
Authenticated MCP and agent gateway for Forge Cascade private AI memory, provenance, graph search, and capsule lineage.
mem0-mcp-server — exposes Mem0 persistent semantic memory as an MCP HTTP server; supports add/search/read/update/delete operations and semantic search for agent memory.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
