Supermemory

Source: original

New Dynamic dreaming is now default

The context cloud

for agents.

Supermemory gives your agents state-of-the-art memory, RAG, user profiles, connectors, and extractors, all built in. Extremely low latency. Works with any model.

Start Building Talk to founder

$ npx supermemory setup Copied Get a personal supermemory

Used by the best teams

〉PRODUCT CATALOG [1/9]

All the legos to build the perfect context for your agent.

Focused primitives for ingesting, understanding, routing, and retrieving context.

  1. 01 Memory & Continual Learning
  2. 02 SuperRAG (Retrieval)
  3. 03 Filesystems
  4. 04 Profiles
  5. 05 Connectors
  6. 06 Extractors
  7. 07 Qualitative Analysis

01 · MEMORY

Memory & Continual Learning

State-of-the-art memory that is persistent, structured, and built as a knowledge graph using our custom user understanding model, powered by dynamic dreaming and a custom graph engine.

02 · RETRIEVAL

SuperRAG (Retrieval)

Hybrid search, reranking, and structured context for documents at sub-300ms latency. The retrieval layer your agent reaches for when it needs more than what's already in working memory.

03 · FILESYSTEMS

Filesystems

A real filesystem mount that gives your agent a supermemory. grep becomes semantic search, a live profile.md synthesizes context on the fly, and any file format is indexed automatically. Native POSIX on macOS and Linux; your agent just uses ls, cat, and grep.

04 · PROFILES

Profiles

Preference, behavior, and identity context that stays coherent across sessions. Your agent remembers the person on the other side of the screen, not just the conversation in front of it.

05 · CONNECTORS

Connectors

Connect Slack, Notion, Drive, Gmail, GitHub, S3, and custom sources; Supermemory automatically keeps them in sync. Changes in your tools are reflected in your agent's memory in real time. No manual imports, no stale context, no ETL.

06 · PARSING

Extractors

Turn PDFs, web pages, images, audio, and raw files into agent-ready memory objects. Smart chunking that preserves meaning across document boundaries, not arbitrary character counts. No need to sign up for 10 different providers; Supermemory handles the extraction for you.

07 · UNDERSTANDING

Qualitative Analysis

Cluster, summarize, and explain user signals without exporting the dataset. The understanding layer runs against your memory in place; your data never leaves the boundary you set.

〉WHAT WE DO [2/9]

Bring your data We build understanding. Your agent just knows.

Context infrastructure for AI agents. One API, every capability.

For developers & teams The Supermemory API State-of-the-art retrieval and memory. RAG, memory, and extraction. One API, every capability. <300ms Recall latency 100B+ Tokens / month #1 On every bench Self-hostable · SOC 2 Type II · TypeScript & Python SDKs Start building in 5 minutes For everyone Personal Supermemory One memory across everything you use. What you teach one AI, every AI remembers. Supermemory App Control panel Claude · Cursor · Codex · OpenCode AI plugins Chrome Extension One-click save 10,000+ power users Get Personal Supermemory

Legacy · A vector database

Stores chunks. Returns chunks. Each session starts from zero.

Supermemory

Facts that evolve. Knowledge that merges, contradicts, and gets forgotten across every session.

〉HOW IT WORKS [3/9]

How it works

How it works.

Four primitives, one graph. Install, ingest, understand, retrieve. Then a fifth step that makes the previous four worth the effort.

01 / PLUG IN

Plug into your stack in minutes.

SDKs for every major language and model harness. Runs in every runtime, from edge functions to long-lived servers.

02 / INGEST

Bring in any type of data, from anywhere.

Supermemory automatically extracts the content for you, in a way that's optimized for retrieval and memory generation.

03 / UNDERSTAND

Entity model learns from raw context.

Our model resolves people, places, and concepts as they evolve over time.

04 / RETRIEVE

Memories form inside our custom graph.

Memory, RAG, and profiles live in the same queryable graph, not isolated vector blobs. One unified structure your agent traverses, not three systems you stitch together.

05 / THEN · REAL-TIME TRAVERSAL

Sub-300ms graph traversal, every request.

Steps 01–04 are the build. This is the payoff: your agent reaches into the graph at request time, not at training time.

〉BENCHMARKS [4/9]

We don't think benchmarks tell the full story.

But we lead every major one anyway. SOTA on LongMemEval, LoCoMo, and ConvoMem.

We also built MemoryBench, an open eval platform for memory systems.

Recall quality,

like the human brain.

Stylized cyan-dithered illustration of a human brain

Recall time

Memories returned in milliseconds, 10× faster than Zep, 25× faster than Mem0.

3D bar chart comparing recall time: Supermemory sub-300ms vs Zep 4s vs Mem0 7-8s

Feature

Best Supermemory

m Mem0

Zep

Memory Graph

Partial

User Profiles

Document Retrieval

Connectors

Document Extractors

Sub-300ms Latency

Self-hostable

Consumer Plugins

Open Eval Platform

Read the full research paper

〉USE CASES [5/9]

Use cases

Best for latency, quality and cost. Or configurable for each use case.

All use cases ↗ ← →

AI Assistants

AI assistants that remember your users.

Persistent context and reasoning memory. Chats, docs, and user data unified so assistants adapt over time.

In production at

ppl.xyz chatnow

Explore Knowledge Bases

Self-improving, for your users.

Ingest, sync, and retrieve from any source, so your agents always have the latest context, not stale snapshots.

In production at

Explore Realtime Knowledge

Realtime knowledge for agents.

Keep your agents grounded in up-to-date facts from every source (docs, APIs, internal tools), synced and retrievable in milliseconds.

In production at

Explore Internal Use

Used by engineers from the best teams.

Internal docs, wikis, and institutional knowledge: searchable and always current for every team member.

In production at

Explore

〉ENTERPRISE [6/9]

Enterprise

Supermemory runs everywhere.

Supermemory runs on-prem, on your cloud, or fully air-gapped — with the same API, the same SLAs, and a paper trail your security team will actually read.

01 / ON PREMISES

In your data center.

Self-host on bare metal or your own Kubernetes. Zero data leaves your perimeter.

02 / YOUR CLOUD

In your VPC.

Deploy to AWS, GCP, or Azure inside your account. BYOC from day one.

03 / LOCAL

On your laptop.

Run the full stack on a workstation for offline dev, demos, or sensitive work.

SOC2

Compliant

SOC 2 Certified

Independent audit confirming that we safeguard your data with the highest security standards.

GDPR

GDPR Compliant

Compliant with EU data protection, ensuring your personal information is handled with care and transparency.

View our security page

〉TESTIMONIALS [7/9]

Testimonials

“We just ditched RAG completely and went memory only through Supermemory.”

Reduced avg response time from 40s → 12s. Using about 40–50% fewer tokens. Just memory & near realtime web-search even for volatile information.

/ Armin Daryabegi, Founder, Chatarmin

Memory vs RAG

Latency (seconds)

40 30 20 10 0

12s

40s

Memory RAG

40%

Fewer tokens

Compared to RAG baseline

View on X

“Tried almost everything — structured memory files, qmd etc. The only thing that works reliably is Supermemory.”

Not facing any memory issues after setting it up.

/ Harshil Mathur, Founder, Razorpay

“Supermemory let us scale usage without losing the thread of every conversation.”

Max Peters, Founder / 〉PRICING [8/9]

Simple pricing, by usage. Pay only for what you use.

Every plan comes with monthly credits. No surprise bills, no upgrade walls — your agent uses what your agent uses.

Free

For builders tinkering, prototypes and sideprojects.

$0 /mo

Start free

Pro

For small teams and plugin power-users.

$19 /mo

Get Pro

Most picked

Max

More headroom for developers who need it.

$100 /mo

Get Max

Scale

For teams running production workloads.

$399 /mo

Get Scale

Enterprise For organizations with committed spend, custom deployments, and security requirements.

Custom

Talk to us

Security & compliance

Scale & performance

Enterprise-grade support

See full rate card and FAQ

〉FAQ [9/9]

FREQUENTLY ASKED QUESTIONS

The fine print, in plain English.

ALL BILLING DEPLOY PROGRAMS

  1. 01 How does the credit balance work?

Every plan comes with a monthly dollar balance. Each API call, storing memories, searching, indexing, draws from that balance at the rates listed above.

When the balance runs out, you can top up or auto top-up to keep going. No surprise bills at the end of the month.

  1. 02 What's an SM token?

SM tokens are the unique tokens Supermemory actually ingests and embeds; repeats and unchanged content don't get billed again. Effectively a 100% discount on what a normal prompt cache would re-charge you for.

Plain text is $0.005 per 1K SM tokens; rich content (PDFs, audio, video) is $0.010 per 1K because it needs heavier extraction.

PLAIN TEXT $0.005 / 1K

RICH CONTENT $0.010 / 1K

  1. 03 What happens if I re-store the same content?

Nothing, you're not billed again. Supermemory deduplicates at the token level, so re-uploading a doc, syncing a connector, or pushing the same conversation history won't redraw from your balance.

Only net-new content counts as SM tokens. This is why production agents that loop over the same context end up an order of magnitude cheaper here than with a typical vector DB.

  1. 04 Do unused credits roll over?

Subscription credits reset monthly. Top-up credits you purchase in advance never expire, they sit in your balance until you use them.

  1. 05 What happens if I exceed my balance?

On Free, you'll be paused; pay-as-you-go isn't available on Free, so you'll need to upgrade to Pro or Scale to keep going.

On Pro and Scale, auto top-up kicks in to keep your app running. You can set hard spend caps on Scale to prevent runaway usage.

  1. 06 Can I self-host?

Self-hosted deployments are available on Scale and Enterprise. Enterprise additionally supports fully air-gapped deployments (LLM inference may be the only outbound dependency, unless GPUs are available).

  1. 07 Do you offer startup or academic research credits?

Yes. Qualifying early-stage startups and academic research teams get $1,000 in credits, dedicated support, and 6 months to build. Apply via the Startup Program link above.

Still something on your mind?

Read the docs Talk to founder

Your Agent Second Brain Workflow needs it’s Supermemory

Start Building

TOTAL MEMORIES SAVED 1,505,650,017