---
title: "past.dev vs Supermemory"
description: "Supermemory provides connectors and multimodal ingestion. past.dev accepts timestamped text and returns ranked documents with dated source excerpts."
canonical: https://past.dev/vs/supermemory
last-updated: 2026-10-09
---
# past.dev vs Supermemory

Source: https://past.dev/vs/supermemory

Supermemory provides context infrastructure for agents. It ingests text, chats, files, PDFs, images and video through extractors and connectors, and provides retrieval and user profiles. past.dev accepts timestamped text and returns ranked documents with dated source excerpts. Choose based on input-format and API requirements.

## What Supermemory is

[Supermemory](https://github.com/supermemoryai/supermemory) describes itself as the long-term and short-term context and memory infrastructure for agents. Its documentation lists memory, retrieval, profiles, connectors, extractors and evaluation as the building blocks, and it takes in raw data in many formats, text, chats, PDFs, images, video and code, through extractors and connectors. It offers a hosted API with SDKs, and the repository, which is MIT licensed, advertises running it yourself.

## What past.dev is

past.dev exposes ingestion, status, recall and deletion, plus audiences and an identity directory. Send text with its original timestamp, including backdated history, wait until ingestion completes, and query it later. `/recall` returns ranked documents with dates and source excerpts for the requested identity.

past.dev does not provide source connectors. Applications call the ingestion endpoint and implement connections to mail, CRM and other source systems.

## Scope differences

|  | Supermemory | past.dev |
| --- | --- | --- |
| Positioning | Context infrastructure for agents, broad | Memory API for timestamped history, narrow |
| Ingestion | Text, chats, files, PDFs, images, video, through extractors and connectors | Text plus optional timestamp and source metadata |
| Connectors to third-party sources | Yes | No, you call the API |
| Time | Facts update as new information arrives | Occurrence timestamp and optional recall timestamp |
| Evidence | Retrieval returns the matching material | Documents include dated source excerpts |
| Abstention | Your code decides | Your code evaluates returned documents |
| Cost visibility | Plan-level | Accounted per call on the console dashboard |
| Self-host | Advertised by the project | Your own cloud, on an Enterprise agreement |

> **Read it at the source**
>
> This table reflects Supermemory documentation and repository information available in August 2026. Check the current documentation before making a deployment decision.

## How to choose

Choose based on the requirements below.

- **Choose Supermemory** if you want one system to ingest everything an agent might read, including files and multimodal content, and you want the connectors rather than writing the ingestion yourself.
- **Choose past.dev** if your problem is a specific one: history arrives as text with dates, the answer changes over time, and you need to show where an answer came from.
- **Documents you own** are worth keeping in your own index either way. [Choosing a vector database for RAG](/vector-database-for-rag) covers that half.

## What this page does not claim

This page contains no head-to-head scores. Our evaluation uses BEAM and LoCoMo with community-corrected answer keys, with full-context and plain-RAG baselines and several judges. The method is published on [benchmarks](/benchmarks). We will publish product comparisons after documenting a reproducible configuration for the other product.

## Related

- [Choosing a vector database for RAG](https://past.dev/vector-database-for-rag)
- [What is agent memory?](https://past.dev/what-is-agent-memory)
- [past.dev vs mem0](https://past.dev/vs/mem0)
- [Memory API overview](https://past.dev/docs/memory-api/overview)
- [How we measure memory](https://past.dev/benchmarks)