MemOS

Plugins in this repository

• @memtensor/memos-local-pluginv2.0.16-beta.1✓

  Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, and three-tier retrieval for OpenClaw, Hermes Agent, and DeepSeek Harness.

  package.json

  apps/memos-local-plugin/package.json

  dsh.bundle.patch

  apps/memos-local-plugin/adapters/deepseek-harness/cordis.patch.yml

  Official core packages (8)

  • @deepseek-ai/cordis^4.0.1shared
  • @deepseek-ai/dsh-agent>=0.1.0-rc.5 <0.2.0shared
  • @deepseek-ai/dsh-llm>=0.1.0-rc.5 <0.2.0shared
  • @deepseek-ai/dsh-session>=0.1.0-rc.5 <0.2.0shared
  • @deepseek-ai/dsh-system-prompt>=0.1.0-rc.5 <0.2.0shared
  • @deepseek-ai/dsh-timeout>=0.1.0-rc.5 <0.2.0shared
  • @deepseek-ai/dsh-tools>=0.1.0-rc.5 <0.2.0shared
  • @deepseek-ai/schemastery^3.18.1shared

Paths are pinned to commit 9119efe5554e

Overview

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.

Required permissions

• No permission declaration is available. Review the source before installing.