Long-term memory plugin for DeepSeek Harness (dsh): four-channel retrieval fusion and continuous memory evolution. Memory construction and retrieval are based on MemGAS (ICLR 2026).
让 DeepSeek Harness 拥有跨会话长期记忆:AI 自动记住你是谁、你的项目和偏好,新会话直接带上背景,生活与工作记忆自动分开互不干扰,零配置无感运行 | Long-term memory for DeepSeek Harness: the AI remembers who you are, your projects and preferences across sessions, keeps personal and work memories separate, zero-config.
Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.
SGME 拾光记忆引擎:AI 全面接管记忆、技能库、WIKI 知识库三大模块,跨会话、多智能体共享记忆,AI 会一直记得你的偏好。ShiGuang Memory Engine · AI takes full charge of three core modules — memory, skills, and wiki knowledge base. Memory is shared across sessions and multiple agents, so your AI always remembers your preferences.
File-based cross-session memory for DeepSeek Harness (DSH) — every memory is a plain Markdown file. 纯 Markdown 存储,无数据库、无 worker、无端口;从 Claude Code 无损迁移记忆与人格,带记忆星图与可选的记忆整理。
Unified fleet-wide agent memory system for DeepSeek Harness — shared Obsidian Vault for dsh, Codex, Claude Code & Hermes with dependency-free Python FTS5 core.
Memory ecosystem bridging the DeepSeek web app and local DSH — one local memory pool shared by a browser extension (harvest/inject), a zero-dependency local service (sole writer), and a DSH adapter (pre-step injection).
DeepSeekBot: the open-source GrokBot alternative, built on DeepSeek Harness (DSH). PersonaBots with their own identity, persona and Git-backed memory you can share via GitHub; group chat, task delegation, and IM identities on Lark/Feishu, Slack, Discord and WeChat. Works with other DSH plugins. Bot marketplace: market.botharness.ai. MIT.