AgentsModelsSkillsMemoryBotsStack FinderEvaluationsGuidesSubmit a resource
Memory Systems

Graphiti

Temporal knowledge graph memory system for agents that need facts, entities, and time-aware context.

Read docs Open repository
Apache-2.0 License
Open sourceSelf-hostedMCP
Graphiti Apache-2.0 License help.getzep.com verified 2026-04-19
About

Graphiti overview

Graphiti is an open-source temporal knowledge graph system from Zep for building agent memory that tracks entities, relationships, and changing facts over time.

✦

Temporal knowledge graph model

Graphiti represents memory as entities and relationships with time-aware context.

This helps agents reason about changing facts instead of flattening everything into chunks.
✦

Agent memory orientation

The project is built for agent and assistant memory workflows.

It focuses on recall structures that matter to agents, not just generic graph storage.
✦

Open-source implementation

The repository and docs provide a concrete path for evaluation.

Graph memory is easier to trust when the implementation is inspectable.
Use cases

When to use Graphiti

Customer or user memory

Track evolving relationships, preferences, and events across time.

Research knowledge graphs

Represent entities and links discovered during research workflows.

Agent context retrieval

Retrieve facts by relationship and recency rather than only semantic similarity.

Compare

How it compares

Graphiti is stronger for relational memory vs vector-only memory

Vector search is useful for fuzzy recall; Graphiti is more appropriate when relationships and time matter.

FAQ

Questions

What should I check before using Graphiti?

Test Graphiti with repeated sessions. Add facts, update them, ask for recall, inspect retrieval behavior, and verify deletion or scoping controls before storing sensitive user or project memory.

Is Graphiti open source?

Graphiti is listed with Apache-2.0 based on the official source links in this profile. Re-check the repository, model card, or docs before production use.

Who should evaluate Graphiti?

Graphiti is most worth evaluating for builders who need graph memory instead of simple chat history.

Tags

Capabilities

memorycontext retrievalragstate managementmcpopen sourceself hostedmcp compatible
Decision brief

Should you use Graphiti?

JSON
Best for
  • Builders who need graph memory instead of simple chat history
  • Teams working with changing entities, relationships, or customer context
  • Developers exploring temporal memory for agent systems
Not for
  • Users who want a fully managed consumer product with no setup work
  • Teams that cannot review the linked source, license, and operational requirements before adoption
Trust and freshness
  • Verified 2026-04-19
  • License: Apache-2.0
  • Repo: getzep/graphiti
  • Open-source signal
Deployment

self hosted

Permission surface

memory, external services

Decision signals

Self-hostable, MCP

Agent packet

Structured decision data for Graphiti

This packet is the compact machine-readable view agents should use before following source links or taking action.

Full JSON Agent packet Markdown brief
Capabilities

memory, context retrieval, rag, state management, mcp

Constraints

open source, self hosted, mcp compatible

Deployment

self hosted

Permission surface

memory, external services

Recommended workflows

Memory or RAG workflow

Overview

What Graphiti does

What it is

Graphiti is an open memory-system resource to evaluate by what it stores, how recall works, how memory is scoped, and whether users or teams can inspect, correct, export, or delete durable context.

Why it matters

Graphiti matters because memory is often relational and time-sensitive. Agents need to know not only what was said, but when it was true and how it connects to other facts.

How to evaluate it

Test Graphiti with repeated sessions. Add facts, update them, ask for recall, inspect retrieval behavior, and verify deletion or scoping controls before storing sensitive user or project memory.

Facts

Known metadata and operating surface

These fields are separated from editorial interpretation so agents can reason over facts and missing checks.

Resource type memory system
Category Memory Systems
Maturity active
Difficulty Unknown
License Apache-2.0
Pricing open source
Verified 2026-04-19
Source confidence high
Risk level moderate
Fit matrix

Where Graphiti fits in an agent stack

strong

Memory or RAG workflow

Graphiti has multiple signals for memory or rag workflow, including matching tags, capabilities, category, or positioning.

  • Create, update, retrieve, correct, and delete memory or retrieval objects with real data.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial

Coding agent workflow

Graphiti has at least one signal for coding agent workflow, but should be checked against a real task before adoption.

  • Run a small repository change and inspect the diff, tests, and rollback path.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial

Connector or protocol layer

Graphiti has at least one signal for connector or protocol layer, but should be checked against a real task before adoption.

  • Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial

Evaluation and observability

Graphiti has at least one signal for evaluation and observability, but should be checked against a real task before adoption.

  • Add one repeatable test case and confirm results can run again in review or CI.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial

Local or private AI stack

Graphiti has at least one signal for local or private ai stack, but should be checked against a real task before adoption.

  • Verify hardware requirements, data path, storage, and whether all calls stay in your environment.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
weak

Browser automation

Graphiti is not primarily positioned for browser automation in the current metadata.

  • Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
Inputs and outputs

What an agent should inspect

Likely inputs

  • Repositories, files, issues, terminal output, and test results
  • Documents, user facts, entities, context, or retrieval queries
  • Tool schemas, API requests, service resources, and auth scopes
  • Official setup instructions and a small real workflow

Likely outputs

  • Diffs, commits, explanations, test results, or review notes
  • Retrieved context, memory updates, graph relations, or citations
  • Scores, traces, regression results, dashboards, or failure cases
  • A decision on whether this resource fits the target workflow
Evidence

Sources, claims, and missing checks

Claims are marked separately from source links so future crawlers and reviewers can update them without rewriting the page.

GitHub github

Repository source for code, license, issues, releases, and implementation details.

 Docs docs

Documentation source for setup, API shape, and operational behavior.
verified

Graphiti is listed as open source.

License metadata: Apache-2.0
verified

Graphiti has a recorded GitHub repository: getzep/graphiti.

Resource facts and GitHub source link.
inferred

Graphiti supports these recorded deployment modes: self hosted.

OpenAgent decision signal metadata.
inferred

Graphiti is tagged with memory, context retrieval, rag, state management, mcp capabilities.

OpenAgent capability taxonomy.
Missing checks
  • Repository freshness has not been recorded.
Next action

How to start evaluating Graphiti

Inspect repository

Check license, recent activity, issues, examples, and security-sensitive code paths.

Open source

Read setup docs

Use docs as the source of truth for installation and supported interfaces.

Open source

Clone Graphiti

Use the official docs for current installation and storage configuration.

git clone https://github.com/getzep/graphiti.git
Compare

Alternatives and nearby resources

Use related resources to compare category fit, license, deployment model, and first-workflow behavior.

Mnemo Cortex

Open-source memory coprocessor for AI agents with persistent recall, semantic search, and crash-safe capture.

Memory Systems OpenLore

Persistent architectural memory for AI coding agents using queryable codebase knowledge graphs and MCP tools.

Memory Systems AgentMemory

Persistent memory for AI coding agents, with benchmarks and local-first workflows.

Memory Systems
FAQ

Common questions about Graphiti

What should I check before using Graphiti?

Test Graphiti with repeated sessions. Add facts, update them, ask for recall, inspect retrieval behavior, and verify deletion or scoping controls before storing sensitive user or project memory.

Is Graphiti open source?

Graphiti is listed with Apache-2.0 based on the official source links in this profile. Re-check the repository, model card, or docs before production use.

Who should evaluate Graphiti?

Graphiti is most worth evaluating for builders who need graph memory instead of simple chat history.