OpenMem ORG

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

MemOS gives AI assistants and chatbots a persistent memory so they can remember past conversations and decisions across sessions, instead of starting completely fresh each time.

Official MemOS Cloud plugin for OpenClaw. Enables long-term memory for agents by recalling context before execution and saving conversations after each run.

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

HaluMem is the first operation level hallucination evaluation benchmark tailored to agent memory systems.

Paper: “MEMRL: SELF-EVOLVING AGENTS VIA RUNTIME REINFORCEMENT LEARNING ON EPISODIC MEMORY” Open-Source Code

MemPrivacy is a privacy-preserving personalized memory management framework for edge-cloud agents.

Text2Mem: A Unified Memory Operation Language for Memory Operating System

MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-Augmented Generation Systems

No description.

Inside Out: PersonaTree, MemListener

Documentation for the repository: https://github.com/MemTensor/MemOS

A Model Context Protocol (MCP) implementation for the Memos API service. This package provides a command-line interface to interact with Memos API using MCP standards.

vllm implementation for paper《SparseX: Efficient Segment-Level KV Cache Sharing for Interleaved LLM Serving》

MemOS backend inference on MacOS

No description.

Provide universal memory capabilities for different AI agents and development frameworks, unifying the capture, retrieval, and management of user, project, and task context.

issues&bugs agent,memos-sentinel

PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue

No description.