DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles,发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目,与 DeepSeek 官方无隶属、授权或背书关系。

Plugin Code Memory — DeepSeek Harness 插件(DSH Plugin)
DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录
← Plugins
P

dsh-plugin-code-memory

Plugin Code Memory

用于 DeepSeek Harness 的本地代码记忆:自动源代码上下文、语义搜索和依赖关系图。

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add github:kobubu/Rag-Coding#8804ad74401b35743729d873e78477bc9a942d31
README兼容性版本

兼容性与来源证明

Plugin Code Memory 以 dsh-plugin-code-memory 发布,当前版本为 0.9.1。Plugin Hub 会校验它的 manifest,并保存精确安装来源,便于复现安装结果。

DSH 兼容范围
*
运行环境
any
发布来源
github
Registry 更新时间
2026/10/19

版本

0.9.1stable
2026/10/19
0.9.0stable
2026/10/18

相关插件

正在加载相关插件…

最新版
0.9.1
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
未提供
文件数
未提供
Surface
any
许可证
未声明
发布源
github
GitHub
★ 0
周下载
0
最近提交
2026/10/19
查看源码 ↗
README Badge

点击下方 Badge 复制 Markdown,粘贴到 README 即可。

这是你的 Plugin?认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库,即可管理这个公开页面。认领后,Hub 会优先安排当前版本的安全扫描,并在通过后公开展示结果。

认领这个 Plugin →
报告问题

相关插件

继续浏览 developer-tools 分类下经过校验的插件。

Web App@deepseek-ai/dsh-web-appdsh 浏览器界面捆绑包:位于 dsh-base 之上的 Web 补丁层,加上运行时粘合插件(提供前端 dist、Web 界面提示符、bash 运行时变量和 URL 行)Sdk Minimal@deepseek-ai/dsh-sdk-minimal独立的最小 SDK 配置包:JSON-RPC、一个 DeepSeek 适配器、持久化 Shell 和 JSONL 会话Sdk App@deepseek-ai/dsh-sdk-appdsh SDK 配置包:基于 dsh-base 提供 stdio JSON-RPC 服务和进程生命周期管理Experimental Inspector Profile@deepseek-ai/dsh-experimental-inspector-profile用于原始 Session 日志和 Chat 节点检查的可选 Web 捆绑包

README

Code Memory for DeepSeek Harness

Give your coding agent the relevant source before its first step. Code Memory (CM) is a local code index and context plugin for JavaScript and TypeScript projects. It combines symbol lookup, dependency graphs, and semantic search to reduce repeated source discovery.

Unofficial community project. Independently developed; not affiliated with or endorsed by DeepSeek.

English · Русский · Download v0.9.1 · Windows installation

What it does

  • Supplies compact source context before the first model call in DeepSeek Harness.
  • Looks up named files and symbols directly; uses local MiniLM embeddings and LanceDB when discovery is needed.
  • Expands relevant dependencies using the TypeScript compiler's symbol and call graph.
  • Checks source versions and avoids repeating unchanged whole files already supplied to Harness.
  • Exposes an MCP server for Codex and Claude Code and an optional UserPromptSubmit hook for automatic context.
  • Includes CM Atlas, a local map of modules, symbols, and their relationships.

The index, embeddings, and graph stay on your computer. Selected code is still sent to your model provider when you use a cloud model. CM does not include model credits or a model-provider subscription.

CM Atlas displaying modules and structural relationships in this public repository

Actual CM Atlas screenshot of this repository's public src directory: 39 modules, 2,409 symbols, and 8,321 relationships. The current Atlas interface is in Russian; the installation guide below is in English.

Measured results, with limits

The published Harness pilot used GPT-6 Luna on six task types in one repository, Geo Dash. Three evaluation series each ran 36 sessions: no CM, the earlier CM, and the newer CM, with two repeats per task and arm.

Newer CM versus no CMPublished result
Total model tokens45–66% fewer across the three series
Estimated model price30–47% lower
Total Harness session time18–37% lower
Independently checked solutions, pooled across series36/36 with newer CM; 35/36 without CM

These are small, single-project pilot results, not guaranteed savings. The ranges are observed series results, not confidence intervals. Costs are estimates; session time does not include first-time installation or indexing. All attempts, including failures, are retained. Earlier approaches and native-client experiments have different outcomes; do not transfer these percentages to every client or workload.

Method, raw results, and reproduction · Codex and Claude Code experiments · What did not work

Install into an existing Harness

Requires DeepSeek Harness 0.2.0-rc.2 and Node.js 24 or 22.19+ within 22.x:

dsh plugin --profile web add github:kobubu/Rag-Coding#v0.9.1

The tag contains the compiled plugin, CLI entry points, and Atlas. CM needs no installation build or Vite/React runtime modules. Then prepare the project index and local model. A ready release tarball is also available:

dsh plugin --profile web add https://github.com/kobubu/Rag-Coding/releases/download/v0.9.1/dsh-plugin-code-memory-0.9.1.tgz

Git tags before 0.9.1 require their release tarball or an explicit source build. The new runtime works with scripts disabled; native dependencies follow the host package manager's policy.

Install on Windows

Download CM-0.9.1-Windows.zip and SHA256SUMS.txt from the v0.9.1 release, verify the checksum, and extract the ZIP. From the extracted folder, run:

powershell -NoProfile -ExecutionPolicy Bypass -File .\install_cm.ps1 -ProjectRoot 'C:\path\to\your-project' -Clients harness

The installer uses a compatible Node.js or downloads a private runtime, installs CM and Harness 0.2.0-rc.2, downloads the embedding model, and prepares your index. Administrator rights and a source checkout are not required. Internet access is required for the initial dependencies and model downloads. Open the generated start-harness.ps1 path printed by setup, then configure your model provider in Harness.

Use -SourceScope src to index a subdirectory. Use -Clients harness,codex,claude to add project MCP connections for all three clients; Codex and Claude Code must be installed separately. Their automatic-context hook is currently a separate manual setup, not an installer default.

Install, launch, verify, and remove · Native-client hook setup

Build from source

Use Node.js 24 LTS, or Node.js 22.19.0+ within the 22.x line.

git clone https://github.com/kobubu/Rag-Coding.git
cd Rag-Coding
npm ci
npm run verify
npm run cm:index
npm run cm:vectors
npm run cm:search -- --query "how are embeddings reused between snapshots"
npm run plugin:smoke

plugin:smoke dispatches tools through the real Harness runtime without a model call. In PowerShell, use npm.cmd for commands that forward flags. For restricted cloud builds, ONNXRUNTIME_NODE_INSTALL=skip npm ci skips the native runtime download; running local embeddings still requires a working ONNX runtime.

The Windows bootstrap is the packaged installation path. A macOS/Linux installer, automatic release updates, and a subscription service are not included.

For source changes, npm run compile rebuilds the runtime. Commit matching dist/src/ and dist/viewer/; npm run package:check and CI reject missing/stale artifacts. The command is named compile because npm treats a script named build as a reason to rebuild Git dependencies.

Documentation

The following engineering documents are currently in Russian; the README and Windows release guide are in English.

DocumentContents
How CM worksRouting, graph expansion, context budgets, and source freshness
Harness integrationBundle installation, configuration, and tools
MCP setupShared local retrieval for coding clients
CM AtlasLocal project visualization
Release notesWhat is included in the public package
Release procedureRebuilding the installer and checking artifacts

CM is written in TypeScript/Node.js. Project code is indexed without being executed. Supported inputs are JavaScript/TypeScript source files; current corpus limits are 500 files and 8 MiB of source. See contribution rules.

Try it on another repository

Show Your Plugins discussion · Community catalog submission

Independent A/B results are welcome: use the same task, model, reasoning settings, checks, and starting commit with CM on and off. Include indexing/setup time separately, all failed attempts, total tokens, elapsed time, and whether the patch actually passes independent checks. Report regressions as well as wins in Issues.