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
Universal memory layer for AI Agents
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
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.
Memory system for autonomous agents - built by an agent, for agents
Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.
10 captures since 2026-05-22
pyproject.toml
· python · 51 dependencies
poetry.lock
· python · 0 dependencies
mem0-plugin/requirements.txt
· python · 1 dependencies
mem0-ts/package.json
· javascript · 36 dependencies
openclaw/package.json
· javascript · 9 dependencies
server/requirements.txt
· python · 17 dependencies
vercel-ai-sdk/package.json
· javascript · 20 dependencies
mem0-ts/pnpm-lock.yaml
· javascript · 482 dependencies
openclaw/pnpm-lock.yaml
· javascript · 333 dependencies
vercel-ai-sdk/pnpm-lock.yaml
· javascript · 285 dependencies
AI agent config detected
Key config paths
.agents
AGENTS.md
CLAUDE.md
.agents
.agents/plugins
.agents/plugins/marketplace.json
AGENTS.md
CLAUDE.md