Mr-remon219/search-boost
Multi-engine web search and evidence synthesis for AI coding agents. Unified MCP server, Pi extension, and DeepSeek Harness bundle — free search, X/Twitter, parallel research, and TUI setup.
Project Overview项目介绍
SearchBoost is a unified open-source tool that provides multi-engine web search and structured evidence synthesis capabilities for AI coding agents. It uses a single shared core runtime and offers dedicated pre-built adapters for multiple popular agent platforms, including standard Model Context Protocol (MCP) servers, Pi, Claude Code, Codex, Cursor, and DeepSeek Harness. You can install it quickly via npm globally, then use the intuitive built-in CLI command to automatically set up full integration for your target agent platform in under a minute, with options for dry-run previews and workspace-specific installs. The tool offers four distinct core functions: fused parallel multi-engine search, smart clean webpage content fetching, public X (Twitter) intelligence, and an experimental adaptive iterative evidence loop.
This tool is built for developers who want their AI coding agents to access up-to-date public web information and synthesize verified evidence for coding or research tasks. It supports native parallel multi-agent research workflows on all hosts that allow subagent deployment, including Cursor, Claude Code, Pi, and DeepSeek Harness. When running a complex research task, it can dispatch separate search worker agents to gather relevant evidence in parallel, then assign a dedicated summarizer agent to produce a clean synthesized output without any extra tool access. It supports both fast response modes for simple queries and deep complex modes for more thorough open-ended research.
SearchBoost requires Node.js version 22.13 or higher to run, and it is released under the permissive open-source MIT license, with no cost for personal or commercial use. You can start using the tool immediately without any API keys, thanks to the built-in free keyless search engine pool that includes Bing, DuckDuckGo, Yahoo, and Exa’s free tier. The tool enforces strict local security: sensitive credentials are stored encrypted with POSIX 0600 permissions, it blocks SSRF attacks, pins target IPs, and rejects SOCKS proxies by default to prevent accidental leaks. If you use a TUN interface with Fake-IP routing, you will need to set the SEARCH_BOOST_TRUSTED_TUN=1 environment variable to allow proper routing.
SearchBoost是一款为AI编码代理提供多引擎网络搜索与证据合成的工具,拥有统一共享核心运行时,可适配MCP协议、Pi代理、DeepSeek Harness、Claude Code、Codex、Cursor等多种环境。它支持同时调用多个搜索提供商并行查询,自带免密钥的免费引擎池,也可添加付费API密钥使用高阶搜索服务,内置网页内容提取、X内容检索等多个工具模块。
它面向需要AI编码代理获取实时外部信息、合成可靠证据的开发者使用,支持多代理并行研究工作流,可将任务分发给多个搜索代理收集证据,再由汇总代理完成内容合成,区分快速响应和复杂研究两种模式。对于需要逐步验证信息的场景,还提供实验性的自适应证据循环,可以按限定步数完成多轮搜索,输出明确的证据覆盖状态。
本项目依赖Node.js 22.13及以上版本,采用MIT许可证开源,无需API密钥即可启动使用。敏感凭据会以加密方式存储在本地私有配置中,默认强制开启SSRF保护和目标IP钉选,明确拒绝SOCKS代理防止网络泄露,若使用Fake-IP路由的TUN接口需要手动设置环境变量放行。
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:search-boost(Mr-remon219/search-boost)
仓库:https://github.com/Mr-remon219/search-boost
本站详情页:https://www.yhbd.top/plugins/mr-remon219-search-boost/
本站登记:类型 bundle · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 38 · 最近提交 2026-10-03 · 主语言 JavaScript
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。
- 38 stars - an early-stage project星标 38,属于早期项目
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 github:Mr-remon219/search-boost
把 Mr-remon219/search-boost 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
Multi-engine web search & evidence synthesis for AI coding agents
One shared core runtime, deeply adapted for MCP, Pi, and DeepSeek Harness
[!NOTE] Release & Branch Notice: The formerly standalone
pi-search-boostanddsh-search-boostprojects are merged into one codebase underlib/. Documented commands specifying@latestretrieve the official published npm package. To test code that is not in a published release, check out the branch or tag you need and follow Installation from Source & Development.
v0.2.4: single-snapshot Jev screening (schema V5), private research save/recovery, bounded PDF text extraction, Desktop integration, and separate package updates / integration management. See the release and migration notes: V3 adaptive inputs/outputs and the
upgradecommand have changed. This source version does not imply npm publication;@latestfollows the published registry.
Table of Contents
- Key Features
- System Architecture
- Supported Hosts Matrix
- Quick Start (30 Seconds)
- Upgrade & Migration Guide
- Interactive Console (TUI)
- Tool Suite & Usage Guide
- Parallel Multi-Agent Research Workflows
- Security
- CLI Command Reference (Headless & CI)
- Installation from Source & Development
- Friendly Links
- License
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 →
reactive-resume/reactive-resume
anywhere-labs/dsh-desktop
dataelement/dsh-desktop
ccch1mneyyy/dsh-TUI
DSH-EAC/DSH-Desktop-EAC
shaobeichen/dsh-pocket
xyTom/coding-tools-mcp