AI Agents

Memary

Longterm Memory for Autonomous Agents with 2,568 GitHub stars.

Status
UnmaintainedNo commits in 676 days.
Last checked
Checked · Oct 12, 2026
License
Open source
Pricing
Free tier · from $0
Visit Memary Compare with alternatives

What it is

Memary is a long-term memory framework designed to enhance the capabilities of autonomous agents. It provides robust storage and retrieval mechanisms that are crucial for maintaining context over time in AI-driven applications.

Memary stands out as a specialized framework for long-term memory management in autonomous agents, offering unique features such as flexible data retrieval mechanisms and scalable architecture.

When it fits — and when it doesn’t

A good fit for

  • Teams developing autonomous agents who need robust memory management

  • Projects requiring long-term data persistence for AI models

  • Developers working on applications that benefit from context-awareness over time

Look elsewhere if

  • Applications needing real-time streaming capabilities (Memary focuses on batch processing)

  • Use cases where minimal setup and configuration are required (Memary requires self-hosting)

Known weaknesses

Each one links to the public issue, changelog or docs page it came from, where we have one.

  1. 01

    Small community and limited third-party integrations

    GitHub repository has few contributors and open issues remain unresolved

What it does well

  • Persistent storage for agent memories

  • Flexible data retrieval mechanisms

  • Scalable architecture to handle large datasets

Pricing

Free tier
YesOpen source — free to use
Paid from
$0
Model
Flat rate
Enterprise plan
No

Pricing not independently confirmed — check the vendor’s page.

Performance benchmarks

How Fast Is It?

Set up Memary

Setup steps, common gotchas and what to check after 30 days.

Open the setup guide →