Graphiti vs Memoria: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of Graphiti and Memoria — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.
Graphiti
getzep (GitHub)
Open-source project to build real-time knowledge graphs and persistent memory stores for AI agents.
Key features
- Real-time Graph Construction: Extracts entities and relationships from incoming text and builds a dynamic graph representation so agent context is stored as structured nodes and edges for fast retrieval.
- MCP-Compatible Server API: Exposes endpoints and protocols aligned with Model Context Protocol patterns to let AI agents query episodes, entities, and contextual graph data as persistent memory.
- Document Ingestion and Registration: Registers documents across multiple formats into the graph store, enabling documents to be linked, searched, and referenced by agents in retrieval workflows.
- Graph Database Integration: Supports integration with graph-backed storage (examples and forks reference Neo4j and FalkorDB) to persist entities, relationships, vectors, and perform graph queries.
- Episode-Based Memory Management: Groups interactions into episodes with metadata (UUIDs, timestamps) to enable chronological context, session tracking, and selective retrieval of past interactions.
- Multi‑Project & Docker Deployment: Community forks and examples provide CLI and Docker Compose setups to run root and project-specific MCP servers, enabling multi-project sharing of a single graph database.
- Developer Tooling & Extensibility: Source-code-first, open repository structure allows customization, extension, and integration into agent stacks and RAG pipelines.
- Extract entities and relationships from text to build knowledge graphs
- Persist graph data in Neo4j graph database
- Model Context Protocol (MCP) server implementation for context serving
- Docker Compose and CLI tooling for quick local deployment and multi-project setups
- Support for project-specific MCP servers sharing a common database (multi-tenant graphs)
- Document registration and ingestion across multiple file formats for RAG workflows
- Integrations/examples showing usage with Cursor and agent systems to store prompts as graph memory
Best for
- Persistent Conversational Memory: Provide chatbots and assistants with long-term memory by storing and retrieving entities and relationships learned across sessions.
- RAG Backend for Document Search: Index and link documents into a knowledge graph so retrieval-augmented generation pipelines can find relevant passages via graph relationships and metadata.
- Agent Context Sharing Across Projects: Run multi-project MCP servers so multiple agents or teams can share and query a centralized knowledge graph for consistent context.
- Debugging and Traceability: Use episode grouping and entity links to trace agent decisions back to source documents and previous interactions for audit and improvement.
- Entity Relationship Discovery: Extract and visualize relationships across ingested content to discover connected concepts, people, locations, or events for analytics or recommendation systems.
- Providing persistent structured memory for conversational AI agents
- Backend for retrieval-augmented generation (RAG) systems using graph storage
- Indexing and searching entities/relations from ingested documents
- Multi-project knowledge graph deployments that share a central Neo4j instance
- Developer experimentation and prototyping of graph-based context for models
Memoria
Anas
On-device photo and video search that indexes the text, speech, objects and faces in your library — no cloud, no account.
Key features
- On-Device OCR: Reads the text inside photos, screenshots, documents, whiteboards and video frames in seven languages, making every written word searchable.
- Local Whisper Transcription: Runs Whisper directly on the device to transcribe the speech in your videos across 99+ languages, so lectures, meetings and voice notes become searchable text.
- Face Detection and Clustering: Detects faces and groups them locally so you can pull up every photo of one person in a single tap, without any cloud face database.
- Object Recognition: Identifies objects in your library so queries like "red bicycle" return matching shots even when nothing was ever tagged.
- Unified Full-Text Index: Combines text, speech, objects and people into one instant search index that lives entirely on the phone.
- Background Indexing: Keeps indexing while the app is closed and prioritises work while the device is charging, so a large library finishes without you babysitting it.
- Zero-Account Privacy Model: No sign-up, no upload and no tracking — analytics are anonymous and opt-out, and the app is GDPR-safe by having nothing to collect.
- One-Time Purchase Unlock: Memoria Plus removes the 250-media indexing cap forever with a single payment processed by Apple or Google, including future on-device models.
Best for
- Finding a Document You Photographed: Recovering an invoice, bill or receipt you snapped months ago by searching the words printed on it rather than scrolling the camera roll.
- Searching Recorded Lectures and Meetings: Locating the moment a specific term was spoken inside a long video by searching the on-device transcript.
- Pulling Every Photo of a Person: Assembling all shots of one friend or family member from a clustered face group for a birthday album or share.
- Recovering Saved Screenshots and Memes: Tracking down a screenshot or meme by the text written on it instead of guessing when you saved it.
- Working Offline or While Travelling: Searching a full media library on a plane or with no signal, since indexing and search never require a network.
- Keeping Sensitive Media Off the Cloud: Making a library of personal, medical or client photos searchable without uploading any of it to a third-party service.