Search

More Filters

Show More
Add Listing
Go Back

A mem

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

A-mem implements an agentic memory system designed to be integrated into LLM agent pipelines to store, index, link and evolve past experiences so agents can reason over history and externalize knowledge. The repository provides a Python package and example usage showing how to add, read, search, update and delete structured notes, how memories are represented with metadata and contextual descriptions, and how the system performs semantic linking and continual refinement. It is intended as infrastructure to help researchers and developers build agents with more advanced long-term memory capabilities rather than a standalone end-user application. The README references a companion paper and experimental results comparing performance across foundation models and indicates the system uses embedding models and vector storage to enable fast semantic retrieval.

Links

Stars
527
App URL
https://github.com/agiresearch/A-mem
Github Repository
https://github.com/agiresearch/A-mem/blob/main/README.md

App Details

Features
The project emphasizes dynamic memory organization inspired by Zettelkasten and agent-driven memory operations. Core components include ChromaDB vector storage for embeddings, automatic note generation with structured attributes (tags, category, timestamp, keywords and context), semantic similarity search and fast retrieval, automated linking of related memories, and continuous memory evolution that updates metadata and connections when memories are added or changed. The system supports multiple LLM backends for generation and reasoning, with examples using OpenAI and Ollama, and demonstrates practical API calls for add, read, search_agentic, update and delete operations. The README also documents best practices for memory creation, retrieval and error handling.
Use Cases
A-mem helps developers and researchers augment LLM agents with a persistent, semantically organized memory layer so agents can leverage past experiences to make more informed decisions and maintain evolving knowledge. By producing structured notes, extracting keywords, and linking related items, the memory system improves retrieval relevance for downstream tasks and supports experiments across multiple foundation models. Its ChromaDB-backed embeddings enable fast semantic search and persistent storage, while flexible metadata and multi-backend LLM support allow integration in both cloud and local setups. The provided examples and guidance reduce integration friction, making it easier to prototype agent workflows that require long-term memory, introspective updates, and automated knowledge network construction.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*