---
slug: "graphiti"
name: "Graphiti"
effect: "Builds temporal knowledge graphs from agent conversations and data, tracking how facts change over time"
category: "memory"
tier: "rising"
url: "https://help.getzep.com/graphiti"
github: "getzep/graphiti"
pricing: "open-source"
license: "Apache-2.0"
tags: ["python", "knowledge-graph", "temporal", "mcp", "neo4j"]
platforms: ["claude-desktop", "cursor", "any-mcp-client"]
install_kind: "pip"
date_added: "2026-10-14"
rank: 17
rising_score: 44
stars: 31759
star_velocity: 39.8
velocity_basis: "since creation"
created_at: "2024-08-08T22:08:30Z"
pushed_at: "2026-10-15T00:19:20Z"
signals_status: "ok"
signals_fetched_at: "2026-10-15T05:02:43.053Z"
page: "https://agenttooldrop.com/tools/graphiti"
---

# Graphiti

Builds temporal knowledge graphs from agent conversations and data, tracking how facts change over time

Category: Memory. Tier: new and rising, rank 17 by new and rising score (44 of 100). Pricing: Open source. License: Apache-2.0.

Platforms: claude-desktop, cursor, any-mcp-client.

## Why you would want it

Graphiti turns episodes (raw text or JSON) into entities and relationships and gives each fact a validity window, so when information changes the old fact is invalidated rather than deleted and you can query what was true at any point. New data is added incrementally without recomputing the graph, and retrieval combines semantic embeddings, BM25 keyword search and graph traversal. Every fact traces back to the episode that produced it, custom entity and edge types are defined with Pydantic models, and a bundled MCP server lets assistants add and search memory.

## Best for

- Agents working on data that changes over time
- Memory that needs provenance back to sources
- Teams comfortable running a graph database

## Use it when

You need agent memory that answers questions about relationships and history, not just similar text chunks.

## Skip it if

You do not want to run a graph database: Graphiti needs Neo4j, FalkorDB or Amazon Neptune plus an LLM with structured output, OpenAI by default. Zep is the managed option from the same team, and anonymous telemetry is on by default (opt out with GRAPHITI_TELEMETRY_ENABLED=false).

## Install

Install with pip:

```sh
pip install graphiti-core
```

Source: https://github.com/getzep/graphiti#readme

## Live signals

Fetched 2026-10-15T05:02:43.053Z (status: ok).

- Repository: getzep/graphiti
- Repository created: 2024-08-08
- Stars: 31,759 (GitHub's count; it cannot be authenticated)
- Stars per day, since repo creation: 39.8 (an average over the repo's life, not a growth rate)
- Forks: 3,266
- Open issues and PRs: 475
- License (GitHub): Apache-2.0
- Last push: 2026-10-15
- Latest release: v0.31.0 (2026-10-14)

## Links

- Website: https://help.getzep.com/graphiti
- GitHub: https://github.com/getzep/graphiti
- Install instructions verified at: https://github.com/getzep/graphiti#readme
- Source for this entry: https://github.com/getzep/graphiti#readme
- AgentToolDrop page: https://agenttooldrop.com/tools/graphiti
- Full catalog (JSON): https://agenttooldrop.com/tools.json