Memary

Visit Tool

Memary is an open-source memory layer for autonomous AI agents, designed to emulate human memory for advanced agent behavior. It allows developers to integrate memory management with minimal implementation.

Claim this tool

2Views

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is Memary?

Memary is an open-source memory layer specifically engineered for autonomous AI agents, aiming to replicate human-like memory functions to enhance agent reasoning and performance. It integrates seamlessly with existing agents, providing features like auto-generated memory, memory modules for tracking user preferences, and system improvement capabilities. Developers can easily manage agent memories, switch between downloaded models, and incorporate custom tools. Memary supports local models via Ollama (Llama 3, LLaVA) and also integrates with OpenAI's GPT models. It utilizes knowledge graphs for efficient information retrieval and offers multi-graph capabilities for managing different agents' memory contexts, particularly with FalkorDB.

Best used for

Ideal for developers and data scientists who need to build and enhance autonomous AI agents with human-like memory capabilities. Especially valuable for integrating memory management with existing agents, tracking user preferences, and leveraging knowledge graphs for efficient information retrieval.

Common actions

manage agent memory

build AI agents

integrate custom tools

track agent preferences

enhance agent reasoning

face swapping"AI Agents"github copilotlow-code/no-codeopen-sourceautomated workflowdeepfakeworkflowscollaboration

Capabilities

Key features

Auto-generated memory
Knowledge graphs
Memory modules
Custom tool integration
Multi-graph support
Local model support

Target Audience

developerdata scientist

Integrations

ollamaopenaiperplexitygoogle-mapsfalkordbneo4j

Pricing & Plans

Open Source

Free

FAQs

What kind of models does Memary support for local execution?

Memary primarily supports local models through Ollama, with suggested defaults including Llama 3 (8B/40B) for LLMs and LLaVA for vision models. It also allows integration with cloud-based models like gpt-3.5-turbo and gpt-4-vision-preview.

How does Memary handle memory and knowledge storage for AI agents?

Memary uses a combination of a Memory Stream and an Entity Knowledge Store. The Memory Stream captures all entities and their timestamps, while the Entity Knowledge Store tracks the frequency and recency of references to these entities, reflecting the agent's depth of knowledge.

Can I use Memary with multiple agents or different user contexts?

Yes, Memary supports multi-graph capabilities, especially when using FalkorDB. This allows users to generate multiple graphs and switch between their IDs, enabling seamless transitions and management of different agents' memory and knowledge contexts.

Trending

Subcategories trending in AI Agents & Automation

AI Frameworks & Infra Chatbots & Conversational AI Workflow Agents Personal Assistants RAG & Document AI Voice Agents

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce