vioscale
Comparison

Mastra vs Memary

No leader: the top candidate Memary has only 0.27 confidence (low), below the 0.35 needed to declare a winner. The attribute-by-attribute breakdown below, with a source and date on every value, is the honest way to compare them.

Mastra full profile →Memary full profile →
Machine formatsJSONMarkdownGraphQLor send Accept: application/json
Mastra55
Memary58
Score
Vioscale score
Mastra55 / 100low · 42%
Memary58 / 100low · 27%
Pricing
Free tier
Mastra✓
Memary✓
Model
Mastracommercial
Memaryfreemium
Price level
Mastrahigh
Memaryfree
Starting price
Mastra$250
Memary–
Transparent
Mastra✓
Memary✓
Integrations
Count
Mastra11
Memary3
Security
Gdpr
Mastra✓
Memary–
Soc2
Mastra✓
Memary–
Vulnerabilities
Adoption
Dependent repos
Mastra0
Memary0
Github stars
Mastra27,493
Memary2,641
Activity
Commits last 30d
Mastra100
Memary–
Release
Cadence days
Mastra4
Memary11
History
Mastra20 items
Memary6 items
License
Spdx
Mastra–
MemaryMIT
Language
Primary
Market
Availability

Capabilities

Feature-by-feature on the axes that matter for agent memory. “-” means undocumented, not absent.

Capabilities
Architecture model
MastraManaged cloud API
MemaryOpen source self hosted
Graph based entity relationship extraction
Mastra-
Memary✓
Automatic context window rolling summarization
Mastra-
Memary-
Semantic vs episodic event chronological memory
Mastra✓
Memary✓
Cross session and multi thread user persistence
Mastra✓
Memary✓
Memory conflict resolution and fact updating
Mastra-
Memary-
Multi tenant user and agent isolation
Mastra✓
Memary✓
Native langchain and llamaindex memory classes
Mastra-
Memary✓
Time decay and recency weighted retrieval
Mastra-
Memary-
Zero data retention and pii redaction layer
Mastra-
Memary-
SOC2 type ii
Mastra-
Memary-
Mit or apache permissive oss license
Mastra-
Memary-
Pricing model
Mastra-
MemaryFree open source

What each one is

The product in its own terms, so the numbers below have context.

Mastra

A TypeScript framework that enables developers to build AI agents and applications using language models and tools, featuring built-in memory management, workflow orchestration, and production observability. Supports both cloud deployment and self-hosted deployment anywhere.

Independently observed

Memary

A memory layer for autonomous agents built on knowledge graphs. It tracks entities, relationships, and events with timestamps, supports multi-agent setups with isolated memory contexts, and integrates with LangChain and LlamaIndex to help agents evolve their knowledge through interactions.

Independently observed

Pricing

List pricing as published by each vendor, with the date we read it. Always verify at the source before you buy.

Mastra

from $250/moHybridFree tier

Free tier + pay-as-you-go. Team plan from $250/month. Enterprise custom.

  • StarterFree
    • 100K observability events/month
    • 24 CPU hours/month
    • 10GB data egress/month
    • 15 days data retention
    • Unlimited users, projects, and deployments
  • Teams$250/month + overage charges
    • 1M observability events/month
    • 250 CPU hours/month
    • 100GB data egress/month
    • 6 months data retention
    • Multiple teams
    • +2 more
  • EnterpriseContact sales
    • Custom volume and retention
    • RBAC
    • Audit logs
    • Uptime SLAs
    • Dedicated support engineer
as of verify ↗

Memary

Open sourceFree tier
as of verify ↗

Platform & deployment

Where each product runs and how it can be hosted. A dash means undocumented, not unsupported.

Platforms
Web
Mastra✓
Memary✓
CLI
Mastra✓
Memary✓
Deployment
Cloud / SaaS
Mastra✓
Memary✗
Self-hosted
Mastra✓
Memary✓

Integrations

What each product connects to. Counts come from the vendor's own integration directory where one exists.

Mastra

11 total
  • OpenAI
  • Anthropic
  • Gemini
  • Slack
  • Discord
  • Telegram
  • Nango
  • Ampersand
  • Paragon
  • Zapier
  • Apideck
Independently observed

Memary

3 total
  • FalkorDB
  • LangChain
  • LlamaIndex
Independently observed

Comparison generated from independently-sourced facts. Every value links to its source and retrieval date. See the method.