---
title: "Zep alternative for temporal memory"
description: "past.dev is a Zep alternative for temporal memory. Compare the temporal model, database, deployment, API surface, and recall output."
canonical: https://past.dev/zep-alternative
last-updated: 2026-10-15
---
# Zep alternative for temporal memory

Source: https://past.dev/zep-alternative

Teams evaluating a Zep alternative can use past.dev, a memory API that runs as a managed service or, on an Enterprise agreement, in your own cloud. Zep uses Graphiti, an open-source temporal graph engine that runs on a graph database. past.dev exposes timestamped ingestion and returns ranked documents with dated source excerpts.

## When to use Zep

[Zep](https://www.getzep.com/) maintains [Graphiti](https://help.getzep.com/graphiti/getting-started/welcome), an open-source temporal knowledge graph. Graphiti ingests episodes, extracts entities and relationships, records time and marks contradicted relationships as expired. It is suitable for teams that want to operate and customize the engine on their own graph database. See [past.dev vs Zep](/vs/zep) for more detail.

## Why teams evaluate alternatives

- **Graph operations.** Graphiti runs on a dedicated graph database, according to its [documentation](https://help.getzep.com/graphiti/getting-started/welcome). Teams must size, secure and upgrade that database.
- **API scope.** Some teams require only ingestion and recall endpoints instead of direct graph operations.
- **Recall output.** Compare the returned documents, dates, source attribution, and the application logic required to determine whether evidence is sufficient.

## How past.dev compares, design to design

| Property | Zep / Graphiti | past.dev |
| --- | --- | --- |
| Time input | Episodes with timestamps | Source text with an occurrence timestamp |
| Delivery | Open-source engine + hosted platform | JSON API: managed, or in your own cloud on an Enterprise agreement |
| Storage you operate | Graph database for self-host | None on the managed service; your own database or cloud account on an Enterprise agreement |
| Recall output | Search results across graph, text and keywords | Ranked documents with dated source excerpts |
| Unanswerable question | Empty or nearest results | Application evaluates returned documents |
| Backfill | Episodes with timestamps | Timestamped ingestion, original dates preserved |

The [benchmarks page](/benchmarks) reports recall, update and abstention results. [How to benchmark agent memory](/benchmarks/methodology) documents the method. We do not publish head-to-head scores without a reproducible configuration.

## When to use each product

- **Choose Zep or Graphiti** when you require an open-source engine, want to customize the graph model and can operate a graph database.
- **Choose past.dev** when you want an API with timestamped ingest and ranked, source-backed recall that runs as a managed service or, on an Enterprise agreement, in your own cloud. The [quickstart](/docs/memory-api/quickstart) shows the integration.

Both products represent time explicitly. See [temporal knowledge graph](/glossary/temporal-knowledge-graph) and [fact supersession](/glossary/fact-supersession) for the underlying concepts.

## Frequently asked questions

### Is past.dev built on Graphiti?

No. past.dev is a separate product with its own public API and recall contract.

### We already run Graphiti. Is there a reason to switch?

A switch may be useful if you want managed operation or recall results measured with a published method. Keep Graphiti if its current deployment and query interface meet your requirements.

## Related

- [past.dev vs Zep, in detail](https://past.dev/vs/zep)
- [mem0 alternative](https://past.dev/mem0-alternative)
- [Temporal knowledge graph](https://past.dev/glossary/temporal-knowledge-graph)
- [How to choose a memory system](https://past.dev/guides/choose-memory-system)
- [How to benchmark agent memory](https://past.dev/benchmarks/methodology)
- [Quickstart](https://past.dev/docs/memory-api/quickstart)