mirror of
https://github.com/supermemoryai/supermemory.git
synced 2026-10-11 03:37:56 +00:00
672defc08b
Rewrites 339 TypeScript calls across 50 pages from the rc.5 `method({ namespace, body })` form to the shipped `method(namespace, { ... })` form, and aligns field names with the live v5 spec: `attach` to `include`, `authUrl` to `authorization`, `lastSync` to `latestRun`, `deletedCount` to `count`, and the paginated `namespaces.list()`.
Renames container tags to namespaces across concepts, connectors, integrations and snippets. The namespace pages keep container tag in the description, search keywords and a rename note so old searches still land, and the v3 reference page points at v5.
The migration guide's SDK table now covers both 5.0.0 SDKs, and the SDK integration page uses the real client options (`baseUrl`, `timeoutInSeconds`, `maxRetries`) and error classes.
65 lines
4 KiB
Text
65 lines
4 KiB
Text
---
|
|
title: "Using Supermemory"
|
|
sidebarTitle: "Overview"
|
|
description: "The full loop: authenticate, put context in, get it back out, keep it correct."
|
|
icon: "/icons/hugeicons/compass-01.svg"
|
|
---
|
|
|
|
import { Journey, JourneyStep, JourneyItem } from "/snippets/journey.mdx";
|
|
|
|
Everything in this section is one of four steps. Same loop whether you're building personal memory, RAG over docs, or both on the same `namespace`.
|
|
|
|
<Journey>
|
|
<JourneyStep number="1" title="Get started">
|
|
<JourneyItem icon="/icons/hugeicons/play.svg" title="Quickstart" href="/quickstart" />
|
|
<JourneyItem icon="/icons/hugeicons/key-01.svg" title="Get an API key" href="/authentication" />
|
|
<JourneyItem icon="/icons/hugeicons/book-open-01.svg" title="API Reference" href="/api-reference/overview" />
|
|
</JourneyStep>
|
|
|
|
<JourneyStep number="2" title="Ingest — get content in">
|
|
<JourneyItem icon="/icons/hugeicons/plus-sign.svg" title="Add memories & documents" href="/ingestion/add-memories" />
|
|
<JourneyItem icon="/icons/hugeicons/clock-01.svg" title="Backfill historical data" href="/ingestion/batch-ingest-historical-data" />
|
|
<JourneyItem icon="/icons/hugeicons/files-02.svg" title="Document operations" href="/ingestion/document-operations" />
|
|
<JourneyItem icon="/icons/hugeicons/plug-01.svg" title="Connectors" href="/connectors/overview" />
|
|
<JourneyItem icon="/icons/hugeicons/files-01.svg" title="Content types" href="/concepts/content-types" />
|
|
<JourneyItem icon="/icons/hugeicons/command-line.svg" title="Ingest API reference" href="/api-reference/ingest" />
|
|
</JourneyStep>
|
|
|
|
<JourneyStep number="3" title="Retrieve — get context back out">
|
|
<JourneyItem icon="/icons/hugeicons/search-01.svg" title="Search" href="/recall/search" />
|
|
<JourneyItem icon="/icons/hugeicons/user.svg" title="User profiles" href="/recall/user-profiles" />
|
|
<JourneyItem icon="/icons/hugeicons/database-01.svg" title="SMFS" href="/smfs/overview" />
|
|
<JourneyItem icon="/icons/hugeicons/command-line.svg" title="Recall API reference" href="/api-reference/search" />
|
|
</JourneyStep>
|
|
|
|
<JourneyStep number="4" title="Manage">
|
|
<JourneyItem icon="/icons/hugeicons/eraser-01.svg" title="CRUD & forgetting" href="/recall/memory-operations" />
|
|
<JourneyItem icon="/icons/hugeicons/check-list.svg" title="Review inferred memories" href="/recall/memory-review" />
|
|
<JourneyItem icon="/icons/hugeicons/settings-02.svg" title="Customizing behavior" href="/concepts/customization" />
|
|
<JourneyItem icon="/icons/hugeicons/justice-scale-01.svg" title="Rules of thumb" href="/concepts/rules" />
|
|
<JourneyItem icon="/icons/hugeicons/command-line.svg" title="Memories API reference" href="/api-reference/memories" />
|
|
<JourneyItem icon="/icons/hugeicons/test-tube-01.svg" title="Benchmark it yourself" href="/memorybench/overview" />
|
|
</JourneyStep>
|
|
</Journey>
|
|
|
|
Raw input automatically becomes memories (the knowledge graph) and indexed document chunks (for RAG). You don't choose one or the other; both come from the same write. Retrieval then gives you three ways to read that pool back. If you're unsure which fits, read [Memory vs RAG](/concepts/memory-vs-rag).
|
|
|
|
## Where next
|
|
|
|
<CardGroup cols={2}>
|
|
<Card title="Quickstart" icon="/icons/hugeicons/play.svg" href="/quickstart">
|
|
Walk the whole loop end to end with one working example.
|
|
</Card>
|
|
<Card title="How it works" icon="/icons/hugeicons/cpu.svg" href="/concepts/how-it-works">
|
|
What happens between `add()` and a memory showing up in search.
|
|
</Card>
|
|
<Card title="Namespaces" icon="/icons/hugeicons/folder-01.svg" href="/concepts/container-tags">
|
|
The isolation boundary every ingest and retrieve call is scoped to (v3/v4 called it a container tag).
|
|
</Card>
|
|
<Card title="Memory vs RAG" icon="/icons/hugeicons/balance-scale.svg" href="/concepts/memory-vs-rag">
|
|
When to reach for search, profiles, or both.
|
|
</Card>
|
|
<Card title="Benchmarking" icon="/icons/hugeicons/test-tube-01.svg" href="/memorybench/overview">
|
|
Run standardized, reproducible evals against Supermemory and other providers — including your own.
|
|
</Card>
|
|
</CardGroup>
|