MemTensor/MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Cursor, Claude Code, Codex, Windsurf, Gemini CLI, GitHub Copilot, Kiro, OpenCode, Antigravity, and Trae.
Universal memory layer for AI Agents
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.
Self-evolving memory across Agent and platform.
1 capture since 2026-05-27