How to use Graphiti: what you can do with it

3 use cases

• Give an agent memory that tracks how facts change

  Store each conversation turn or record as an episode so the graph keeps what is true now and what was true before.

  • REPO getzep/graphiti
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • Research
  • Advanced
  View prompt

  Using getzep/graphiti, install it with `pip install graphiti-core`, start Neo4j with `docker compose up`, ingest <my conversation log> as episodes, and show me one fact that was invalidated by a later episode.

  Share Email me this

• Build a private knowledge graph with local models

  Run extraction and embeddings through Ollama's OpenAI-compatible endpoint so no data leaves your machine.

  • REPO getzep/graphiti
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • Research
  • Advanced
  View prompt

  Using getzep/graphiti with a local Ollama server, configure OpenAIGenericClient and OpenAIEmbedder as the README shows, ingest <my notes folder>, and report how many entities were extracted and any extraction failures.

  Share Email me this

• Shape the graph with your own entity types

  Declare entity and edge types as Pydantic models so the graph follows your domain, or let structure emerge from the data.

  • REPO getzep/graphiti
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • Research
  • Advanced
  View prompt

  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.

  Share Email me this

Quick start with Graphiti

1. Check you have what it needs: 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.
2. Open getzep/graphiti on GitHub and read the README and license.
3. Install the library with pip install graphiti-core and set OPENAI_API_KEY in your environment
4. Start a graph database with docker compose up for Neo4j, or docker compose --profile falkordb up for FalkorDB
5. Follow the Quickstart Example to connect, build the indices and constraints, and add text and JSON episodes
6. Query with hybrid search for relationships and rerank results by graph distance

These steps come from our top use case, Give an agent memory that tracks how facts change, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for getzep/graphiti

claude mcp add --transport http deduped https://dedupedai.com/mcp

Best AI repos for Research

About this repo

• Who it is forDevelopers building agents or assistants whose knowledge changes over time and who will run their own graph database.
• Why it is hot32k stars, talked about in 2 AI sources we track
• LanguagePython
• Sourcegithub.com/getzep/graphiti · Back to Hot repos

Requirements

• 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

Related repos

• Trended earlier REPO OpenMOSS/OpenETA OpenETA OpenETA is a Python embodied task agent that runs a continuous observe, reason, act, verify loop across simulators and real robots.
• Trended earlier REPO Luciole-Studio/Misaka-Agent Misaka Agent MISAKA is a Python multi-agent research system for the humanities and social sciences that turns one question into a reviewed research graph and a sourced research article.
• Trended earlier REPO TencentCloud/TencentDB-Agent-Memory TencentDB Agent Memory A team-level memory server for AI agents that stores chat memory, skills, wiki pages, and code graphs, and shares them across agents and frameworks.