Graphiti vs nodeterm: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of Graphiti and nodeterm — 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
nodeterm
Enes Kırca
A node-based terminal manager that puts real terminals and coding agents as draggable nodes on an infinite canvas, with tmux-backed persistent sessions.
Key features
- Everything Is a Node: Right-click the infinite canvas to open a terminal, an AI agent, a sticky note, a Monaco editor, a diff view or a web/video node, then arrange them spatially like a map instead of stacking tabs.
- Persistent tmux Sessions: Every node runs in its own tmux session, so quitting the app or restarting the machine restores each terminal and agent exactly where it left off.
- Hook-Driven Agent Status: Pulsing RUNNING and NEEDS YOU badges come from agent hooks rather than output scraping, with subagent cards showing live transcripts, a per-node context meter, OS notifications and MacBook notch presence.
- In-Node Permission Prompts: Click the notification when an agent blocks, answer the permission prompt directly in the node, and get told the moment the turn completes.
- Kanban View of Live Sessions: Toggle any project between canvas and a Trello-style board with a keyboard shortcut; cards are the running sessions and open into the real terminal with members, due dates, priority and comments.
- Wired Agent Context: Draw an edge between two agent nodes so each can read the other's context on demand, and branch a conversation into a fresh node without losing the original thread.
- Three Surfaces, One Session: Run nodeterm as a macOS/Linux desktop app, as a self-hosted browser app via Server Edition, or from an iOS companion paired by QR code that continues the same live session end-to-end encrypted.
- On-Device Voice Input: Hold a keyboard shortcut to dictate to a terminal using on-device Whisper, review the transcription and send it, with audio never leaving the machine.
Best for
- Parallel Agent Supervision: Run Claude, Codex and Gemini side by side as canvas nodes and see at a glance which one is working and which one is waiting on you.
- Long-Running Session Recovery: Keep multi-hour agent runs and build shells alive across app restarts and machine reboots without rebuilding your terminal layout.
- Multi-Project Context Switching: Give each project its own canvas of grouped terminals, notes and diffs so switching projects restores the whole mental model rather than a tab bar.
- Agent Work Tracking: Manage in-flight agent tasks on a kanban board where each card is a real running session, moving work across columns without interrupting it.
- Remote Development Access: Self-host Server Edition and reach the same live sessions from a browser or the iOS companion when away from the main machine.
- Context Handoff Between Agents: Wire one agent node into another so a research agent's findings feed an implementation agent without copy-pasting transcripts.