Compare
Lumi vs MemoryGraph
Graph-based MCP memory server focused on coding agents, whereas Lumi targets general LLM chat memory.
LumiYour AI finally remembers you. No more starting from zero.
MemoryGraphGraph based MCP Memory Server for AI Coding AgentsSide by side
- What it is
- Lumi:Lumi adds persistent, searchable memory to Claude, ChatGPT and Gemini so AI remembers your context across sessions.
- MemoryGraph:MemoryGraph provides graph-based persistent memory for AI assistants via the Model Context Protocol.
- Best for
- Lumi:Persistent memory layer for LLMs
- MemoryGraph:Graph-structured memory for AI agents
- Who it’s for
- Lumi:Developers and AI enthusiasts who use LLMs and need cross-chat context.
- MemoryGraph:Developers building AI coding agents that need long-term, relational memory.
- Pricing
- Lumi:Freemium
- MemoryGraph:Freemium
- Plans
- Lumi:—
- MemoryGraph:PRO $5/month per month · ULTRA $50/month per month · TEAM $100/month per month
- Open source
- Lumi:—
- MemoryGraph:Yes, 247 GitHub stars
- Works with
- Lumi:Claude, ChatGPT, Gemini
- MemoryGraph:Claude (Desktop/Code), custom GPT implementations, any MCP-compatible assistant
- DevHunt upvotes
- Lumi:1
- MemoryGraph:7
- Launched on DevHunt
- Lumi:May 2026
- MemoryGraph:Dec 2025
Lumi features
- Cross-LLM Memory. Store and retrieve context across Claude, ChatGPT and Gemini from a single vault.
- Semantic Search. AI-powered search finds relevant memories by meaning, not just keywords.
- Vault Organization. Create vaults and collections with hierarchical control to structure memories.
- Document Upload. Upload PDFs and docs for instant retrieval-augmented generation without setup.
- End-to-End Encryption. AES-256 at rest, TLS 1.3 in transit, row-level isolation and 30-day backup deletion.
- MCP OAuth Connect. Connect your tools in ~60 seconds via MCP token authentication.
MemoryGraph features
- Automatic memory capture. Stores solutions, patterns and decisions automatically as the agent works.
- Graph relationships. Creates typed edges (e.g., SOLVES, DEPENDS_ON) to enable multi-hop, temporal queries.
- Semantic recall. Fuzzy, relevance-based search across stored memories with recall_memories().
- Backend flexibility. Supports SQLite, FalkorDBLite, FalkorDB server, Neo4j, Memgraph and future cloud backend.
- Data portability. Migrate, export to JSON, and rollback memories between backends without lock-in.
- Cloud sync & team workspaces. Managed cloud backend shares memories across devices and teams with SSO support.
Based on each tool's website and DevHunt data. Details may change; check the official sites.