nowledge-mem-deepseek-harness
by nowledge-co
给所有 AI 工具和 Agent 共用的一层记忆:注入 Context Bundle、提示时检索、MCP 工具与回合结束 DSH 线程捕获。
One memory layer for every AI tool and agent: Context Bundle injection, prompt-time recall, MCP tools, and turn-end DSH thread capture.
安装
dsh plugin --profile web add github:nowledge-co/nowledge-mem-deepseek-harnessGitHub 源码安装:首次需按提示配置 allowBuilds 构建授权后重试
安装与环境配置指引、插件开发教程见 DSH 中文社区文档 ↗
安装即在你的机器上以你的权限运行第三方代码——它可读写文件、使用凭据、访问网络,DSH 的工具审批不会为插件代码加沙箱。「检测到 manifest」仅代表发现 dsh.bundle / dsh.plugin 清单,不构成兼容性或安全审查;安装前请审阅源码,不熟悉的插件先在不含密钥的环境试用。
README
目录
One memory layer for every AI tool and agent, packaged as a DeepSeek Harness (dsh) bundle. Nowledge Mem brings DSH into the same durable memory system as your other agents, with startup context, prompt-time recall, MCP memory tools, and turn-end thread capture.
This repository is the canonical standalone plugin package, mirrored in nowledge-co/community for the Nowledge Mem connector index.
Install
dsh plugin --profile web add github:nowledge-co/nowledge-mem-deepseek-harness
dsh web
For a local checkout of nowledge-co/community, run this from the repository root:
dsh plugin --profile web add ./nowledge-mem-deepseek-harness-plugin
dsh web
Make sure the nmem CLI is on PATH, then verify:
nmem status
nmem config mcp show --host deepseek-harness
The bundle connects to the local Mem MCP endpoint by default:
http://127.0.0.1:14242/mcp/
For Nowledge Cloud or another remote Mem, set:
export NMEM_MCP_URL="https://<workspace>/mcp"
export NMEM_API_KEY="<mem-api-key>"
What It Does
- Injects the Nowledge Mem Context Bundle once per DSH session through
agent/pre-step. - Runs prompt-time memory recall for continuation, release, regression, connector, plugin, and other recall-shaped prompts.
- Adds the Mem MCP server through DSH's reconnecting
@deepseek-ai/dsh-mcp-client, so tools appear asmcp__nowledge_mem__.... - Imports the real DSH surface transcript after completed turns with
nmem t import --source deepseek-harness. - Stamps CLI imports with
NMEM_IMPORT_ORIGIN=deepseek-harness.
Configuration
The bundle accepts these row config fields in a later cordis.patch.yml override:
- id: nowledge-mem
config:
cliPath: nmem
sourceApp: deepseek-harness
importOrigin: deepseek-harness
contextOnSessionStart: true
recallOnPrompt: true
syncOnTurnEnd: true
recallLimit: 8
spaceId: my-space-id
agentId: deepseek-harness
Ambient variables also work:
NMEM_SPACENMEM_AGENT_IDNMEM_HOST_AGENT_IDNMEM_MCP_URLorNOWLEDGE_MEM_MCP_URLNMEM_API_KEY
Model Experience
Startup Context
The model sees one plugin-sourced user message containing the current Nowledge Mem Context Bundle. It is marked as form: "snapshot" and reminds the model that it is cross-tool context, not an instruction override.
Prompt-Time Recall
When the user asks to continue, remember, review previous work, ship a release, debug a regression, or discuss connectors/plugins, the plugin calls:
nmem --json m search "<prompt>" -n 8
The model sees a bounded recall message with memory titles, source hints, scores, and content.
MCP Tools
Mem MCP tools are registered through DSH's MCP bridge under the nowledge_mem namespace. DSH currently bridges MCP tools only; MCP resources and prompts are not surfaced by the Harness client.
Thread Capture
After each completed DSH turn, the plugin serializes user, assistant, and tool-result events, skips its own injected context messages, and imports the transcript into Mem as source=deepseek-harness.
Known Limitations
- DeepSeek Harness is in developer preview, so public package APIs may change.
- Historical DSH sessions are not backfilled by this package yet; it captures new sessions while the plugin is active.
- The DSH MCP bridge exposes tools only, so Nowledge Mem resources/prompts are not shown through MCP today.
- Turn capture depends on the local
nmemCLI being available in the DSH process environment.
Community Position
The canonical public repository is nowledge-co/nowledge-mem-deepseek-harness, tagged with dsh-plugin for DeepSeek Harness ecosystem discovery. The community repository keeps a registry/index mirror for Nowledge Mem surfaces.
原始 README: https://github.com/nowledge-co/nowledge-mem-deepseek-harness/blob/main/README.md ↗
同类插件
查看全部 →
mnemon
LLM监督持久内存插件 — 基于图的召回,跨会话知识,单二进制。与DeepSeek Harness、Claude Code、OpenClaw及任何代理运行时兼容。

memtrace-public
面向 AI 编码 agent 的结构化记忆:双时态图谱、MCP 原生、零 LLM 调用;支持 Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf

dsh-flowix-memory
将本地 flowix-cli 注册为 MCP 服务,让 agent 可以搜索、读取、创建和编辑 Flowix 备忘与思维导图产物。

flowix
笔记助你,记忆助你的代理。

engramory
AI代理的便携式内存协议 — 以静态规则加载;整理学科 + 参考规范 + 可选的钩子API

dsh-memory-evolve
为 DeepSeek Harness 提供纯插件实现的跨会话长期记忆与后台自我进化能力:五轨记忆、Git 分支感知、回合内自我审查、技能自我进化与技能管理器、四轨待办、COI 调度、会话广播、会话搜索、提示词管理器和临时信息便签;零核心修改、零运行时依赖,安装即用,卸载即净。