dsh-self-improved
DeepSeek Harness 长期记忆与自进化插件：L0 对话捕获 → L1 记忆提取 → L2 场景归纳 → L3 用户画像，自动召回注入 + 技能合成，纯本地（SQLite FTS5 + jieba，可选向量召回）。
Long-term memory & self-evolving plugin for DSH: L0 capture → L1 memory extraction → L2 scene grouping → L3 user persona, auto recall injection, skill synthesis, fully local (SQLite FTS5 + jieba, optional vector recall).
怎么安装
dsh plugin add dsh-self-improved 简介
dsh-self-improved **Long-term memory & self-evolving plugin** for DeepSeek Harness (fully local). Status: M0–M6 complete and deployed to a real environment (web profile). Design/research docs stay local only (see .gitignore). What it is Adds the two missing capabilities to DSH — "cross-session memory + self-evolution": **Memory**: automatically distills key points from conversations (facts / preferences / events / instructions) into a local memory store; before each new turn, relevant memories are injected to the model — the AI "remembers you". **Self-evolution**: memories are consolidated, de…
推荐参考
信息
- 协议
- MIT
- 语言
- TypeScript
- GitHub 星标
- 5
- 月下载
- 261
- 最近更新
- 2026-08-15
- 创建于
- 2026-08-15
基础安全检查
- 检查结果
- 无
- 收录来源
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- 主题标签
- agent-memory, ai-agent, deepseek-harness, dsh, dsh-plugin, fts5, long-term-memory, memory, privacy, self-improvement, skill-synthesis, sqlite
同类推荐
hindsight
vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents
Hindsight：会学习的 Agent 长期记忆系统，自动召回/保存、知识页、深度反思与按仓库隔离的记忆银行。
firecrawl-mcp-server
firecrawl/firecrawl-mcp-server
🔥 官方Firecrawl MCP服务器 - 为Cursor、Claude及任何其他LLM客户端添加强大的网页抓取和搜索功能。
markdownify-mcp
zcaceres/markdownify-mcp
用于将几乎任何内容转换为Markdown的Model Context Protocol服务器。