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.
The code for NeurIPS 2025 paper "A-Mem: Agentic Memory for LLM Agents"
| Date | Stars |
|---|---|
| 2026-08-04 | 934 |
| 2026-08-06 | 934 |
| 2026-08-13 | 941 |
| 2026-08-18 | 943 |
| 2026-08-20 | 945 |
| 2026-08-21 | 944 |
| 2026-08-22 | 945 |
| 2026-08-24 | 945 |
| 2026-08-25 | 946 |
| 2026-08-26 | 947 |
| 2026-08-29 | 948 |
| 2026-08-30 | 949 |
| 2026-08-31 | 950 |
| 2026-09-01 | 952 |
| 2026-09-02 | 955 |
| 2026-09-03 | 956 |
| 2026-09-04 | 957 |
| 2026-09-05 | 957 |
| 2026-09-07 | 959 |
| 2026-09-08 | 961 |
| 2026-09-10 | 963 |
| 2026-09-13 | 964 |
| 2026-09-14 | 967 |
| 2026-09-15 | 968 |
| 2026-09-17 | 971 |
| 2026-09-19 | 971 |
| 2026-09-20 | 973 |
| 2026-09-21 | 974 |
| 2026-09-22 | 975 |
| 2026-09-26 | 974 |
| 2026-09-30 | 976 |
| 2026-10-02 | 977 |
| 2026-10-05 | 978 |
| 2026-10-07 | 979 |
| 2026-10-08 | 980 |
| 2026-10-09 | 982 |
| 2026-10-10 | 983 |
| 2026-10-12 | 985 |
| 2026-10-13 | 988 |
| 2026-10-14 | 992 |
| 2026-10-15 | 995 |
| 2026-10-17 | 996 |
| 2026-10-19 | 997 |
| 2026-10-20 | 999 |
| 2026-10-21 | 999 |
| 2026-10-22 | 1001 |
| 2026-10-24 | 1002 |
| 2026-10-25 | 1003 |
| 2026-10-26 | 1005 |
| 2026-10-27 | 1008 |
| 2026-10-30 | 1009 |
| 2026-11-01 | 1009 |
| 2026-11-02 | 1010 |
| 2026-11-04 | 1013 |
Today
+3 stars today
This week
+5 stars this week
This month
+35 stars this month
Momentum
17.0
growth rate 0.50%/day
# Agentic Memory 🧠 A novel agentic memory system for LLM agents that can dynamically organize memories in an agentic way. > **Note:** This repository is specifically designed to reproduce the results presented in our paper. If you want to use the A-Mem system in building your agents, please refer to our official implementation at: [A-mem-sys](https://github.com/WujiangXu/A-mem-sys) For more details, please refer to our paper: [A-Mem: Agentic Memory for LLM Agents](https://arxiv.org/pdf/2502.12110) > 🔥 **News (Oct 2026):** We provide a stronger version of A-Mem, **FlexA-Mem: Budget-Adaptive Agentic Memory for LLM Agents** ([paper](https://arxiv.org/html/2610.33274v1), [code](https://github.com/WujiangXu/Flex-Amem)). FlexA-Mem keeps A-Mem's linked notes but uses them as the compressed history itself: at every step, the agent sees the whole history as a timeline of notes, and the notes most relevant to the current step are expanded in place into their raw content or excerpts, so the prompt fits any token budget. It is evaluated on LongMemEval-S, LoCoMo, SWE-bench Verified and AppWorld. ## 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> ## Key Features ✨ - 🔄 Dynamic memory organization based on Zettelkasten principles - 🔍 Intelligent indexing and linking of memories - 📝 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. Generates comprehensive notes with structured attributes 2. Creates contextual descriptions and tags 3. Analyzes historical memories for relevant connections 4. Establishes meaningful links based on similarities 5. Enables dynamic memory evolution and updates ## 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/WujiangXu/AgenticMemory.git cd AgenticMemory ``` 2. Install dependencies: Option 1: Using venv (Python virtual environment) ```bash # Create and activate virtual environment python -m venv a-mem source a-mem/bin/activate # Linux/Mac a-mem\Scripts\activate # Windows # Install dependencies pip install -r requirements.txt ``` Option 2: Using Conda ```bash # Create and activate conda environment conda create -n myenv python=3.9 conda activate myenv # Install dependencies pip install -r requirements.txt ``` 3. Run the experiments in LoCoMo dataset: **Option A — Original evaluation (requires OpenAI JSON schema support):** ```bash python test_advanced.py ``` **Option B — Robust evaluation (recommended, works with any LLM backend):** The robust evaluation (`test_advanced_robust.py`) removes
Excerpt of 6,575 characters
Read on GitHub
Wujiang Xu · Meta, Rutgers University · United States
32
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:e7a497f700c048c4, desc:agentic