sandbaseai/sandbase-harness
开源、兼容CMA的代理运行时,适用于任何模型,具备MCP工具、沙箱会话、审计、回放和本地控制台。包含一个基于stdio MCP的原生DeepSeek Harness集成包。
Project Overview项目介绍
SandBase Harness is an open-source local-first AI agent runtime that runs on your own machine or your own private infrastructure. It comes with built-in support for persistent sessions, sandboxed tool execution, memory management, credential storage, and full audit trails, plus a native web console for managing agents and custom agent development. It integrates with various major model providers including OpenAI, Anthropic, and DeepSeek, and fully supports the core Model Context Protocol for connecting to different types of external tools and services. It can be easily integrated with DeepSeek Harness and other popular AI agent platforms.
It supports multiple sandbox environments including local, Docker, and Kubernetes, so you can choose the level of isolation that fits your use case. It offers persistent sessions, resumable event streams, audit logging, and replay functionality, plus credential vaults, permission policies, and access approval controls for tool usage. All data is stored locally in SQLite and files, so you don’t need a third-party hosted control plane to run your agents. This runtime is ideal for developers and teams that want full control over their AI agent infrastructure without relying on external services.
To install the latest stable runtime, you first clone the v0.3.8 release branch with a depth of 1, install npm dependencies, build the project, then initialize your agent project and start the local server. After startup, you can open http://127.0.0.1:3000/dashboard to access the convenient web console. SandBase Harness is released under the open-source Apache 2.0 license, and is listed across multiple community-maintained DeepSeek Harness plugin directories. It is part of the larger SandBase ecosystem that includes shared agent skills, a cross-platform CLI tool, and a plugin store for DeepSeek Harness.
SandBase Harness 是一个优先本地运行的 AI 代理运行时,提供会话管理、沙箱工具调用、记忆存储、凭据管理、审计追踪能力,还自带内置控制台,可运行在个人设备或自有基础设施上。它支持多个主流 AI 模型提供商,包括 OpenAI、Anthropic、DeepSeek 等,兼容 Model Context Protocol 工具集,可集成到 DeepSeek Harness 等多个代理平台使用。
它提供本地、Docker、Kubernetes 多种沙箱运行方式,支持持久会话、可恢复事件流、审计重放,还有凭据库、权限策略、访问审批等工具访问控制能力。存储采用优先本地的 SQLite 和文件存储,不需要托管控制平面,适合需要搭建自有 AI 代理基础设施的开发团队和个人开发者使用。
安装需要先克隆指定版本的仓库,安装 npm 依赖后编译构建,再初始化项目即可启动,访问本地 3000 端口就能打开控制面板。项目采用 Apache 2.0 开源许可证,目前已经适配多个 DSH 插件目录,同时维护了 SandBase 生态相关的技能集、CLI 工具等周边项目。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:sandbase-harness(sandbaseai/sandbase-harness)
仓库:https://github.com/sandbaseai/sandbase-harness
本站详情页:https://www.yhbd.top/plugins/sandbaseai-sandbase-harness/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 Apache-2.0 · ⭐ 681 · 最近提交 2026-10-03 · 主语言 TypeScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- This site's static screen found no obvious risk signal (stars, license, activity, manifest)本站静态筛查没发现明显风险信号(星标、许可证、更新活跃度、清单完整度)
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add git+https://github.com/sandbaseai/sandbase-harness.git
把 sandbaseai/sandbase-harness 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
SandBase Harness
AI-readable project metadata: llms.txt · installation guide
A local-first runtime for AI agents. Sessions, sandboxed tools, memory, credentials, audit trails, and a built-in Console — all running on your machine or in your own infrastructure.
Building with DeepSeek Harness? The independent DeepSeek Harness Handbook provides source-backed runtime guides, multilingual troubleshooting, and a regularly updated Agent-first resource map.
Quick Start
Requirements: Node.js 22+, npm 10+, and a model provider API key (OpenAI, Anthropic, MiniMax, or any OpenAI-compatible endpoint). Docker is optional and only needed for Docker-backed sandboxes.
git clone --branch v0.3.8 --depth 1 https://github.com/sandbaseai/sandbase-harness.git
cd sandbase-harness
npm ci
npm run build
mkdir ../my-agents && cd ../my-agents
node ../sandbase-harness/dist/index.js init
node ../sandbase-harness/dist/index.js start
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
1692775560/dsh-Mimir-Academic-research
PerryLink/dsh-memento
WeirdSky924/agent-handoff-skill
1na-ko/dsh-hdc-bridge