MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
- 12k
- TypeScript
- Apache-2.0
- 2 h ago
MemTensor
Built from MemTensor's public GitHub profile. Not on Take My Repo yet, so there are no posts or updates here.
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.
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
Paper: “MEMRL: SELF-EVOLVING AGENTS VIA RUNTIME REINFORCEMENT LEARNING ON EPISODIC MEMORY” Open-Source Code
Metis is the memory foundation model series developed by Metis Group, MemTensor.
HaluMem is the first operation level hallucination evaluation benchmark tailored to agent memory systems.
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
PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue
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.
Provide universal memory capabilities for different AI agents and development frameworks, unifying the capture, retrieval, and management of user, project, and task context.