sandbaseai/sandbase-harness 预览 preview

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。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 no risk signal found未发现风险信号
  • 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

English | 中文

GitHub stars Listed on deepseek-plugin.org Release Official MCP Registry Discussions CodeQL License

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.

SandBase Harness architecture

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 →

← 上一个 Prev dsh_desktop 下一个 Next Minke →