agentscope-ai/ReMe
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
This tool helps AI agent developers give their agents a persistent memory. It tackles the common problems of agents forgetting past interactions due to limited context windows and starting every new session from scratch. You can input conversation logs and important facts, and it outputs a more intelligent agent that remembers user preferences, past conversations, and learns from previous tasks. It's designed for developers building AI agents for personal assistants, customer service, coding help, or task automation.
2,185 stars. Actively maintained with 36 commits in the last 30 days.
Use this if you are developing an AI agent and need it to remember past interactions, user preferences, or learn from its operational history across multiple sessions.
Not ideal if you are looking for a general-purpose database or a memory solution for human users rather than AI agents.
Stars
2,185
Forks
161
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
36
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/agentscope-ai/ReMe"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Compare
Related tools
MemoriLabs/Memori
SQL Native Memory Layer for LLMs, AI Agents & Multi-Agent Systems
volcengine/OpenViking
OpenViking is an open-source context database designed specifically for AI Agents(such as...
mem0ai/mem0
Universal memory layer for AI Agents
zjunlp/LightMem
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
MemTensor/MemOS
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill...