Updated

Graphiti

Zep's open-source Python library for temporal knowledge graphs that agents update in real time, with dated facts, stored in a graph database you run (Neo4j, FalkorDB, Kuzu or Amazon Neptune).

4 open-source projects declare Graphiti in their code; 1 maker's product we track uses it.

Open sourceSelf-hostableFree tier

Profile checked

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use Graphiti

Makers' products we track use Graphiti for agent memory (1).

What Graphiti is used for

Agent Memory · Open-source library →A Python library for temporal knowledge graphs that agents update in real time, on Neo4j, FalkorDB, Kuzu or Neptune.Trade-off: A library, not a service — you run the graph database and pay for the LLM calls that extract entities and facts.
Letta3Mem02Supermemory2Graphiti1Zep0Makers' products on each, for agent memory

When to use Graphiti, and when not

Pick Graphiti if

  • Memory must stay on your own infrastructure, built as a graph over your data. Agent Memory →
  • Your agent needs dated facts that change over time, from business data as well as chats. Agent Memory →

Something else fits better if

  • You want to add user memory to an existing agent with a few API calls and a free tier to start: Mem0 or Supermemory.
  • You'd rather build the agent on a platform where memory is built in: Letta.
  • You want memory as plain Markdown files you can read, edit and share across your own AI tools: Basic Memory.
From each decision's guide, written from what makers' products chose and why.

How Graphiti itself is built

16 tools, from its own code, website and Product Hunt page.

Who uses it

1 makers' products, each linked to the source that shows it, and 4 open-source projects that declare it in their code. The best known on Product Hunt: Ringo (20 followers).

The maker says so 1Declared in code 4How evidence is collected →
Ringo
RingoSeamless AX Co-worker

“Graphiti was essential for building the custom RAG architecture for Ringo. It perfectly handles dynamic data, allowing us to create highly personalized AI models tailored to each company workspace.”

Agent MemoryMaker says so · source ↗

Open source: a project that declares Graphiti as a dependency in its public code — verifiable, but not necessarily a live product.

Alternatives to Graphiti

All alternatives by situation →

Questions makers ask about Graphiti

What is Graphiti used for?

Zep's open-source Python library for temporal knowledge graphs that agents update in real time, with dated facts, stored in a graph database you run (Neo4j, FalkorDB, Kuzu or Amazon Neptune). Makers' products we track use it for agent memory (1).

When should you use Graphiti?

Memory must stay on your own infrastructure, built as a graph over your data (agent memory). Your agent needs dated facts that change over time, from business data as well as chats (agent memory). Something else fits better if: you want to add user memory to an existing agent with a few API calls and a free tier to start, pick Mem0 or Supermemory; you'd rather build the agent on a platform where memory is built in, pick Letta.

Is Graphiti free?

Yes — it is free, open-source software.

Is Graphiti open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with Graphiti?

No llms.txt, official MCP server or CLI found yet.

Who uses Graphiti?

1 makers' products we track, each with a source, and 4 open-source projects declare it in their code. The best known of them on Product Hunt: Ringo (20 followers). source ↗