agiresearch/A-mem

A-MEM: Agentic Memory for LLM Agents

51
/ 100
Established

This project offers a sophisticated memory system designed for AI agents that interact with complex tasks. It takes raw text inputs, like observations or project notes, and dynamically organizes them into an interconnected knowledge base, allowing the agent to recall and apply past experiences more effectively. AI researchers and developers building intelligent agents that need to learn and adapt over time would use this.

883 stars.

Use this if you are building an LLM agent and need a memory system that can intelligently organize, link, and evolve its knowledge, going beyond basic storage and retrieval.

Not ideal if you are looking for a simple, static memory store without advanced organizational and evolutionary capabilities, or if your agent's tasks do not require dynamic learning from past interactions.

AI-agent-development LLM-memory-management intelligent-system-design knowledge-representation autonomous-agents
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

883

Forks

94

Language

Python

License

MIT

Last pushed

Dec 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/agiresearch/A-mem"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.