#3 in AI Development PlatformsUpdated 2026-08

Supermemory

by Supermemory · Memory and retrieval layer for AI agents

82.4 — BenchRank score out of 100

Homepage
Pricing page

Visit website See full AI Development Platforms ranking

Overview

Supermemory is a context layer for AI agents that combines memory, retrieval, user profiles, connectors and extractors behind one API. Ingested data is resolved into a knowledge graph holding memory, RAG and profiles together, which agents query at request time via semantic search and graph traversal in a single call. A personal app, Chrome extension and plugins for AI coding tools are also offered.

Best for: Developers giving AI agents persistent memory and retrieval through a single hosted API.
Pricing: Free tier with about $5/month of usage included, then $19, $100 or $399 per month with $20, $130 and $600 of usage built in respectively, billed against usage rates from $0.001 per 1K SM tokens, with custom Enterprise pricing.
Runs on: WebmacOSSelf-hostedCLI

Strengths and trade-offs

Strengths

One API covers memory, RAG, profiles, connectors and extractors
TypeScript and Python SDKs; self-hosting available on higher plans
Repeat content is deduplicated and not billed again
Free tier includes ~$5/month of usage, no card required

Trade-offs

Self-hosting only on Scale ($399/mo) and Enterprise
Free plan pauses when the balance runs out; no pay-as-you-go
Hard spend caps are limited to Scale and Enterprise
Subscription credits reset monthly and do not roll over

Pricing

Published plans from Supermemory’s own pricing page, in USD. Usage charges and add-ons may apply on top.

Supermemory pricing tiers, monthly rates in USD
Plan	Monthly	Includes
Free	—	~$5/mo of usage built in Hermes Plugin and Supermemory MCP Community support
Pro	$19	~$20/mo of usage built in, auto top-up available Google Drive, Notion and OneDrive connectors 2 teammates included, unlimited storage Email support
Max	$100	~$130/mo of usage built in (6× Pro) Gmail and Granola connectors on top of Pro OpenClaw, Claude Code and other plugins Priority support
Scale	$399	~$600/mo of usage built in, auto top-up plus spend caps All connectors (Gmail, GitHub, S3, Web Crawler) Up to 10 teammates SOC 2, HIPAA BAA and a self-hosted option
ENTERPRISE	Contact sales	Air-gapped self-hosting or a dedicated managed instance SOC 2, HIPAA, GDPR, custom contracts and DPA Committed-spend pricing and custom rate limits Uptime SLA, dedicated account manager, forward deployed engineer

How this score is made up

Each dimension is scored out of 100 and combined into the headline score using fixed weights.

MCP support: 92 out of 100
API quality: 55 out of 100
Documentation: 80 out of 100
Agent friendliness: 98 out of 100
Pricing transparency: 100 out of 100
Changelog: 100 out of 100
Marketing site structure: 75 out of 100
Operational trust: 60 out of 100

Measured, but not part of the score

Useful to know, but not a mark for or against the product — so these do not affect the ranking.

Openness: 85 out of 100
Maintenance: 100 out of 100

This doesn’t look right — report a problem with Supermemory’s score

Alternatives in AI Development Platforms

Ranked 1
84.6 — BenchRank score out of 100
Mem0
Mem0 · Hosted memory layer for AI agents, with Python and Node SDKs
Best for: Developer teams adding persistent memory to AI agents through a hosted API, with a free tier
Ranked 2
84 — BenchRank score out of 100
Nango
Nango · Code-first integration platform covering 900+ APIs
Best for: Product teams building many third-party API integrations into a SaaS product or AI agent
Ranked 4
78.1 — BenchRank score out of 100
LLM Gateway
LLM Gateway · Unified OpenAI-compatible API for 40+ LLM providers
Best for: Developers routing requests across many LLM providers through one OpenAI-compatible API.