> Documentation index: https://rift.sh/llms.txt

# Rift vs Supermemory

Supermemory turns conversations and documents into searchable memory on its servers. Rift syncs files between machines without reading them.

### What Supermemory is

Supermemory is a memory and retrieval service for agents and apps. You send it text, files, chats or connected sources such as Drive and Notion, and it extracts facts into a graph, keeps the source passages for search and maintains a profile for each user. One API returns all three. It can also mount a namespace as a directory through an open-source tool called SMFS, so an agent can run ls, cat and grep on its memory. It is a hosted platform, and a single-machine server that you run yourself is free within a licence limit.

### How they differ

Supermemory processes what you send so it can extract facts, build embeddings and answer searches by meaning, and on the hosted platform that work happens on Supermemory's servers. Its SMFS tool syncs a mounted directory through those servers, which index it. Rift does not index or interpret anything. It moves files between the machines whose keys were given access.

- Identity
  - Supermemory: A Supermemory API key for one organization, or a key limited to one namespace.
  - Rift: A key that each machine and agent makes for itself. No account.

- Smallest share
  - Supermemory: One namespace, through an API key limited to it.
  - Rift: A folder, a subfolder or one file, as read or write.

- Who checks access
  - Supermemory: Supermemory's servers, or your own server when you host it.
  - Rift: Each machine that receives a file checks the grant itself.

- Who can read your files
  - Supermemory: Supermemory, on the hosted platform, where its models process what you send. You, when you host it with a local model. A hosted model you point it at sees what it processes. We found no documented option for customer-held keys.
  - Rift: Only the machines you shared with. Rift Cloud holds ciphertext.

- When your machines are off
  - Supermemory: Memories and mounted files stay available from the hosted platform.
  - Rift: Files stored in Rift Cloud stay available.

### Which to choose

Choose Supermemory when

- Agents need to recall facts about a user across sessions.
- You want search by meaning over documents with no embedding pipeline to run.
- You want connectors that pull from Google Drive, Notion or Gmail.

Choose Rift when

- The files should reach other machines without a service indexing them.
- A cloud should store the files and be unable to read them.
- Another person's agent needs one folder and should hold its own key.

### Using them together

An agent can keep what it has learned in Supermemory and the files it works on in Rift.

[Use Rift with Supermemory](https://rift.sh/docs/use-with/supermemory.md)

Based on Supermemory's documentation and privacy policy, read in October 2026. Sources: [what it is](https://supermemory.ai/docs/overview/what-is-supermemory.md) , [how it works](https://supermemory.ai/docs/concepts/how-it-works.md) , [SMFS](https://supermemory.ai/docs/smfs/overview.md) , [security](https://supermemory.ai/docs/overview/security.md) , [API keys](https://supermemory.ai/docs/authentication.md) , [namespaces](https://supermemory.ai/docs/concepts/container-tags.md) , [SMFS mount](https://supermemory.ai/docs/smfs/mount.md) , [self-hosting](https://supermemory.ai/docs/self-hosting/overview.md) , [privacy policy](https://supermemory.ai/privacy/).