DeepSeek Harness插件市场
返回目录
Agent 与会话技能

dsh-self-improved

madage/dsh-self-improved

DeepSeek Harness long-term memory & self-evolving plugin: L0 capture -> L1 memory extraction -> L2 scene grouping -> L3 user persona, auto recall injection + skill synthesis, fully local.

去 GitHub 查看项目主页

OVERVIEW

数据概览

Star
11
Fork
1
开放 Issue
2
最后推送
2026/08/16 04:59:44

PROJECT TOPICS

项目标签

agent-memoryai-agentdeepseek-harnessdshdsh-pluginfts5long-term-memorymemoryprivacyself-improvementskill-synthesissqlite
PROJECT README README展开收起

正在读取 GitHub README...

MORE IN CATEGORY

同类插件

浏览分类
Agent 与会话插件精选

dsh-agent-team-gui

toolclub

Persistent multi-model workflow teams for DeepSeek Harness — dynamic lead planning, bounded DAGs, per-agent model/tools, Run Center and Token insights.

agentagent-orchestration
168TypeScript2026-08-15
Agent 与会话插件精选

dsh-memory

FuRongJun-1999

白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。

agent-safetyagentic-ai
136TypeScript2026-08-14