Apache-2.0 本地優先 Agent 執行階段，以外掛形式安裝進 DeepSeek Harness：內建 MCP stdio 橋接，向 DSH 提供沙箱工作階段、稽核、回放與本機主控台。
DSH 整合
相容
作者聲明
安全稽核
未稽核
最後核實
2026-08-21
授權條款
Apache-2.0
01它能幫你完成什麼？
Run sandboxed, auditable agent sessions from inside DeepSeek Harness
DSH can list agents, create and run sessions, stream turns, inspect results and artifacts, and stop work through native mcp__sandbase__* tools
DSH users who want a self-hosted agent runtime with sandboxing, audit trails and replay behind their DSH profile
Execute generated agent code safely in isolated sandboxes
Session sandboxes on local process, Docker (per-session containers), Kubernetes (kubectl exec/cp), or a self-hosted worker queue, plus audit trails and replay
Teams running untrusted or generated code who need sandbox boundaries, credential handling and auditability
Operate any model provider, including DeepSeek V4, from one local-first runtime
A single configured model provider boundary (OpenAI, Anthropic, MiniMax, or OpenAI-compatible endpoints) driving agents and sessions, with SQLite metadata kept local
Developers who want model-agnostic agents without a required hosted control plane
02如何將外掛接入 DeepSeek Harness？
先決條件
- DeepSeek Harness (dsh) installed with a profile available (the README example uses `--profile web`)
- Node.js 22+ and npm 10+
- A model provider API key (OpenAI, Anthropic, MiniMax, or an OpenAI-compatible endpoint)
- Docker (optional, for Docker-backed sandboxes)
安裝步驟
- 01
Clone the tagged release and build: `git clone --branch v0.3.7 --depth 1 https://github.com/sandbaseai/sandbase-harness.git`, `cd sandbase-harness`, `npm ci`, `npm run build`
$ git clone --branch v0.3.7 --depth 1 https://github.com/sandbaseai/sandbase-harness.git
- 02
Create a workspace and start the runtime: `mkdir ../my-agents && cd ../my-agents`, `node ../sandbase-harness/dist/index.js init`, `node ../sandbase-harness/dist/index.js start`
- 03
Point DSH at the running runtime: `export MANAGED_AGENTS_URL=http://127.0.0.1:3000`
- 04
Install the bundle into a DSH profile and boot it: `dsh plugin --profile web add -w ../sandbase-harness`, then `dsh web`
$ dsh plugin --profile web add -w ../sandbase-harness
驗證整合成功
- Open `http://127.0.0.1:3000/dashboard`, go to Settings > Models, paste your API key — the README says "you're running"
03DSH 整合程度與能力邊界
Installed into a DSH profile as a third-party plugin (`dsh plugin --profile web add -w ../sandbase-harness`); a bundled MCP bridge over stdio exposes agents, sessions, streamed turns, artifacts and cancellation as native mcp__sandbase__* tools
DeepSeek Harness MCP bridge
a running SandBase Harness runtime reachable at MANAGED_AGENTS_URL→agents, sessions, streamed turns, artifacts and cancellation exposed to DSH as native mcp__sandbase__* tools over stdio
Sandboxed session execution
agent sessions with generated code or tool calls→isolated execution on local process, Docker (per-session containers), Kubernetes (kubectl exec/cp), or self-hosted worker queue
Docker-backed mode starts per-session containers; local mode writes session sandboxes and workspace snapshots to the .managed-agents state directoryPersistent sessions with audit and replay
running agent sessions→persistent sessions, resumable Server-Sent Events for replay and debugging, and audit trails stored in SQLite
writes SQLite metadata (data.db), logs, uploaded files and skill bytes to the workspace state directoryMulti-provider model operation
one configured provider boundary via Settings (OpenAI, Anthropic, MiniMax, or OpenAI-compatible endpoints, including DeepSeek V4)→agents and sessions served against the chosen model provider
model requests go over the network to the configured provider; an API key is required
04適合誰？何時不該用？
適合
- DSH users who want a self-hosted agent runtime with sandboxing, audit trails and replay behind their DSH profile
- Teams running untrusted or generated code who need sandbox boundaries, credential handling and auditability
- Developers who want model-agnostic agents without a required hosted control plane
不適合
- The unscoped `managed-agents` name on npm is not this project. Install only from the tagged GitHub source release; do not run `npx managed-agents` or `npm install managed-agents`.
- The runtime API is open by default; authentication only activates once at least one API key exists (static MANAGED_AGENTS_API_KEY or a managed key), so keys should be configured before exposing the port beyond localhost.
05相容性、維護與安全提醒
- The unscoped `managed-agents` name on npm is not this project. Install only from the tagged GitHub source release; do not run `npx managed-agents` or `npm install managed-agents`.
- The runtime API is open by default; authentication only activates once at least one API key exists (static MANAGED_AGENTS_API_KEY or a managed key), so keys should be configured before exposing the port beyond localhost.
- Requires Node.js 22+, npm 10+ and a model provider API key to run; Docker is additionally required for Docker-backed sandboxes, and Codespaces usage may be billed by GitHub.
Apache-2.0 · actively maintained (latest release v0.3.7, 2026-08-20)
06常見問題
如何把 SandBase Harness 安裝到 DeepSeek Harness？
複製帶 tag 的發布版本，用 npm 建置，在工作區 init 並啟動執行階段，設定 MANAGED_AGENTS_URL=http://127.0.0.1:3000，然後執行 `dsh plugin --profile web add -w ../sandbase-harness` 和 `dsh web`。DSH profile 會直接安裝經過驗證的原始碼簽出，而不是 npm 套件。
這個整合是原生的還是走 MCP？
它是 DSH 外掛：安裝 bundle 後 DSH 會透過 stdio 啟動內建的 MCP 入口，把 Agent、工作階段、串流回合、產出物和取消操作暴露為原生 mcp__sandbase__* 工具。
安裝前需要準備什麼？
Node.js 22+、npm 10+、一個模型供應商 API 金鑰（OpenAI、Anthropic、MiniMax 或 OpenAI 相容端點），如需 Docker 沙箱還要安裝 Docker。執行階段必須已啟動，保證 MANAGED_AGENTS_URL 可存取。
我的資料會存在哪裡？
本地優先：SQLite 元資料、上傳檔案、技能包、快照和工作階段沙箱都儲存在工作區的 `.managed-agents` 狀態目錄；模型請求發往你自行設定的模型供應商，不需要任何託管控制平面。
需要 SandBase 帳號或 npm 套件嗎？
當 DSH 已提供網頁/搜尋工具時無需 SandBase 帳號。另外 npm 上未加 scope 的 `managed-agents` 名稱並非本專案——只應從帶 tag 的 GitHub 原始碼發布安裝。
07相關的 DSH 工作流程
archify
作者 tt-a1i
為編碼智慧體生成美觀可驗證的架構圖、時序圖與資料流圖，輸出自包含 HTML，支援動效與清晰匯出。
openviking
作者 volcengine
為 AI 智慧體打造的自進化上下文資料庫，統一智慧體記憶、知識 RAG 與技能。
nocobase
作者 nocobase
開源的 AI + 無程式碼應用搭建平臺：AI 在久經生產驗證的底層基礎設施與所見即所得的無程式碼介面之上工作，幫你快速構建 CRM、ERP 等業務系統，兼顧速度與可靠性。
learn-harness-engineering
作者 walkinglabs
Harness 工程新手教程，從 0 到 1 系統學習智慧體工作流框架。
08資料與來源
Run this project as a DSH plugin instead of treating `dsh-plugin` as discovery metadata only. Install the bundle into a…
DeepSeek Harness bridge over MCP stdio for agents, sessions, streamed turns, artifacts, and cancellation
此頁面根據專案公開文件、儲存庫中繼資料與 DSH Plugins 的結構化解析所產生；最後核實於 2026-08-21。發現錯誤？提交更正。
最佳 DeepSeek Harness 外掛
從全目錄挑出的 12 個值得優先安裝的外掛，涵蓋各個分類。