dsh-experience
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@dsh-experienceHow did I solve git push TLS timeout before?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
dsh-experience
一个跨会话经验知识库(自主进化)。它把 agent 在任务中踩过的坑、探索出的解决方案, 沉淀成可复用的"问题 → 解决方案"经验,让模型在新会话遇到类似问题时检索并复用—— 不重新训练,越用越强。
对应前沿:WebCoach(arXiv 2511.12997)的跨会话记忆三组件;Evo-Memory 的 test-time evolution 思想。数据源是 DSH 已有的 session 日志。
三组件(对应 WebCoach)
组件 | 文件 | 作用 |
Condenser(压缩) |
| 把会话轨迹压缩成"问题→解决方案"经验(离线,用 flash) |
Memory Store(存储) |
| 持久化经验库 |
Coach(检索) |
| 新会话遇到问题,检索相关经验(零 LLM) |
Related MCP server: Librarian
核心原则
运行时零 LLM:检索默认是纯词法(IDF 加权 + 中文 bigram),查询时不花任何 token;
可选本地语义检索:启动本地 embedding 服务(见下)后,检索升级为语义匹配 (bge-large-zh,本地 GPU/CPU,零云端成本),解决同义词/表述差异;服务未启动时 自动降级词法;
离线才用大模型:只有
extract.mjs提取经验时调 flash(批量、事后);自主进化:
extract.mjs+add_experience持续沉淀,库随任务增长;重复经验自动去重。
语义检索(可选,本地 embedding)
缓存里若已有 BAAI/bge-large-zh-v1.5(或联网可下载),启动本地服务:
python embed-server.py # 默认 127.0.0.1:8001,需 transformers+torchstore.mjs 检测到该服务后,检索从"词法"自动升级为"语义"(bge 中文 embedding +
query/doc 分离 + 余弦相似度,阈值 0.45 过滤无关,recency 微调);服务挂了则回退词法。
用法
1. 离线提取经验(唯一用大模型的地方)
node extract.mjs --latest # 从最新会话提取
node extract.mjs --all # 从所有会话提取
node extract.mjs <sessionDir> # 指定会话目录2. 运行时检索(MCP 工具)
把 index.mjs 挂进 DSH(见下方),agent 遇到问题时可调:
mcp__experience__search_experience("git push GitHub TLS 超时怎么办")
→ 返回过去会话里解决过这个问题的经验其余工具:add_experience(手动沉淀)、list_experiences(浏览)。
挂进 DSH
在 cordis.patch.yml 的 insert: 里加:
- id: mcp-experience
name: '@deepseek-ai/dsh-mcp-client'
config:
serverName: experience
transport: stdio
command: '<node 路径>'
args:
- '<本目录>/index.mjs'经验条目结构
{
"id": "…",
"problem": "问题一句话",
"solution": "解决方案(含命令/文件/配置细节)",
"keywords": ["关键词"],
"sourceSession": "session-…",
"createdAt": "ISO"
}测试:node test.mjs(分词 / 检索 / 持久化)。
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityAmaintenanceProvides AI agents with persistent knowledge storage, enabling them to store, search, and retrieve text, documents, and files using semantic and keyword search via MCP tools.31Apache 2.0
- Alicense-qualityDmaintenanceAn MCP server enabling AI agents to record, query, and share structured problem-solving experiences with human review and confidence decay.10MIT
- Alicense-qualityBmaintenanceProvides persistent, cross-session memory for CLI agents via MCP tools, enabling them to recall, distill, and share experiences across projects and tools.6MIT
Related MCP Connectors
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/keyiadiannao/dsh-experience'
If you have feedback or need assistance with the MCP directory API, please join our Discord server