Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A-MEM: Agentic Memory for LLM Agents
| Date | Stars |
|---|---|
| 2026-07-31 | 376 |
| 2026-08-01 | 376 |
| 2026-08-06 | 376 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Agentic Memory 🧠
A novel agentic memory system for LLM agents that can dynamically organize memories in an agentic way.
## Introduction 🌟
Large Language Model (LLM) agents have demonstrated remarkable capabilities in handling complex real-world tasks through external tool usage. However, to effectively leverage historical experiences, they require sophisticated memory systems. Traditional memory systems, while providing basic storage and retrieval functionality, often lack advanced memory organization capabilities.
Our project introduces an innovative **Agentic Memory** system that revolutionizes how LLM agents manage and utilize their memories:
<div align="center">
<img src="Figure/intro-a.jpg" alt="Traditional Memory System" width="600"/>
<img src="Figure/intro-b.jpg" alt="Our Proposed Agentic Memory" width="600"/>
<br>
<em>Comparison between traditional memory system (top) and our proposed agentic memory (bottom). Our system enables dynamic memory operations and flexible agent-memory interactions.</em>
</div>
> **Note:** This repository provides a memory system to facilitate agent construction. If you want to reproduce the results presented in our paper, please refer to: [https://github.com/WujiangXu/AgenticMemory](https://github.com/WujiangXu/AgenticMemory)
For more details, please refer to our paper: [A-MEM: Agentic Memory for LLM Agents](https://arxiv.org/pdf/2502.12110)
## Key Features ✨
- 🔄 Dynamic memory organization based on Zettelkasten principles
- 🔍 Intelligent indexing and linking of memories via ChromaDB
- 📝 Comprehensive note generation with structured attributes
- 🌐 Interconnected knowledge networks
- 🧬 Continuous memory evolution and refinement
- 🤖 Agent-driven decision making for adaptive memory management
## Framework 🏗️
<div align="center">
<img src="Figure/framework.jpg" alt="Agentic Memory Framework" width="800"/>
<br>
<em>The framework of our Agentic Memory system showing the dynamic interaction between LLM agents and memory components.</em>
</div>
## How It Works 🛠️
When a new memory is added to the system:
1. **LLM Analysis**: Automatically analyzes content to generate keywords, context, and tags (if not provided)
2. **Enhanced Embedding**: Creates vector embeddings using both content and generated metadata for superior retrieval
3. **Semantic Storage**: Stores memories in ChromaDB with rich semantic information
4. **Relationship Analysis**: Analyzes historical memories for relevant connections using enhanced embeddings
5. **Dynamic Linking**: Establishes meaningful links based on content and metadata similarities
6. **Memory Evolution**: Enables continuous memory evolution and updates through intelligent analysis
## Results 📊
Empirical experiments conducted on six foundation models demonstrate superior performance compared to existing SOTA baselines.
## Getting Started 🚀
1. Clone the repository:
```bash
git clone https://github.com/agiresearch/A-mem.git
cd A-mem
```
2. Install dependencies:
Create and activate a virtual environment (recommended):
```bash
python -m venv .venv
source .venv/bin/activate # On Windows, use: .venv\Scripts\activate
```
Install the package:
```bash
pip install .
```
For development, you can install it in editable mode:
```bash
pip install -e .
```
3. Usage Examples 💡
Here's how to use the Agentic Memory system for basic operations:
```python
from agentic_memory.memory_system import AgenticMemorySystem
# Initialize the memory system with OpenAI 🚀
memory_system = AgenticMemorySystem(
model_name='all-MiniLM-L6-v2', # Embedding model for ChromaDB
llm_backend="openai", # LLM backend (openai/ollama/sglang/openrouter)
llm_model="gpt-4o-mini" # LLM model name
)
# OR initialize with SGLang for faster local inference 🚀
memory_system = AgenticMemorySystem(
model_name='all-MiniLM-L6-v2',
llm_backend="sglang", # Use SGLang backend
llm_model="meta-llama/Llama-3.1-8B-Instruct", # Excerpt of 11,913 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:82f92361b095a046, desc:agentic