DEDUPEDsecurity. The reference MCP and REST servers have no authentication or prompt-injection protection; do not expose them to an untrusted network.
Who it is forA team modeling customers, products or policies that need a predictable schema.
The problemLearned structure alone can produce inconsistent entity types across documents.
The outcomeA graph whose nodes and edges use your prescribed types, with room to add learned ones later.
What you need first
- Python 3.10 or higher; install with `pip install graphiti-core`
- A graph database: Neo4j 5.26, FalkorDB 1.1.2, Amazon Neptune, or Kuzu (deprecated)
- An OpenAI API key by default, or another provider such as Anthropic, Gemini, Groq or a local Ollama server
Steps
- Install a backend extra, for example
pip install graphiti-core[falkordb] - Define entity and edge types as Pydantic models (prescribed ontology)
- Ingest episodes and compare the result with what learned ontology produces
- Disable telemetry if you need to with
export GRAPHITI_TELEMETRY_ENABLED=false
Prompt for your agent
Using getzep/graphiti, define Pydantic entity types for <my domain>, ingest <sample records> as episodes, and list the entity types that ended up in the graph.
Caveat. Graphiti is a framework, not a hosted memory product; you run the database, retrieval and service around it.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for getzep/graphiti and "Shape the graph with your own entity types"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer