N
nguyenvanduocit/research-kit
Toolkit to help you get started with Spec-Driven Research
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
2026-11-14 实测：注册表里没有这个包（E404），照原样敲会失败。
安装与配置
- 复制上面的命令
- 粘成
claude_desktop_config.json里mcpServers的一项（本地服务器用 command + args，示例见 客户端接法） - 重启客户端
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"nguyenvanduocit-research-kit": {
"command": "uv",
"args": ["tool", "install", "research-cli"]
}
}
}解析自我们于 2026-11-07 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"nguyenvanduocit-research-kit": {
"command": "uv",
"args": ["tool", "install", "research-cli"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio nguyenvanduocit-research-kit -- uv tool install research-cli
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- 来源明细
- 收录自 abordage/awesome-mcp 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-11-05 · 最近见到 2026-11-14 · 共见到 10 次 · 被 10 个来源列出
- 评分构成
- 综合分 1,003 · 10 个来源 · mcp
- 安装
uv tool install research-cli
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
uv tool install research-cli。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
我们收录于 2026-11-05；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
Research Kit
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
Deep Research Toolkit for AI Agents
An open source toolkit for conducting structured, rigorous research with AI agents. Move beyond ad-hoc queries to systematic investigation with quality standards and reproducible methodologies.
## Origin & Motivation
Research Kit is a fork of Spec Kit by GitHub, originally built as a personal project to adapt the Specification-Driven Development (SDD) workflow for systematic research.
The deeper motivation behind this project is to demonstrate a simple but powerful idea: AI agents perform significantly better when guided by multiple structured phases and template constraints. Instead of asking an AI to "do research" in a single open-ended prompt, Research Kit breaks the process into 10 distinct phases, each with its own template, quality standards, and output expectations. This structured approach:
Reduces hallucination by constraining AI output to specific, well-defined templates at each phase
Improves consistency by enforcing the same methodology across different research topics
Enables quality control by making each phase reviewable before proceeding to the next
Produces better results by giving the AI clear context boundaries instead of unbounded instructions
If you've ever noticed that AI gives better answers when you break a complex question into smaller parts, Research Kit applies that principle systematically to the entire research workflow.
For details on what changed from the upstream Spec Kit, see The Fork.
## Table of Contents
Origin & Motivation
What is Research Kit?
The Problem
Who It's For
Key Features
Quick Start
Research Workflow
Research Types
Supported AI Agents
Installation
Research CLI Reference
Example Output
Documentation
Prerequisites
Troubleshooting
Contributing
License
## What is Research Kit?
Research Kit is a structured research framework designed for AI agents. It transforms ad-hoc prompting into systematic investigation by providing:
Multi-phase research workflow - From defining research questions to executing comprehensive studies
Quality standards enforcement - Built-in principles for source evaluation, methodology rigor, and bias mitigation
Research type specialization - Tailored approaches for academic, market, technical, and general research
Reproducible methodologies - Documented approaches that can be validated and replicated
Citation management - Integrated BibTeX support for proper source attribution
AI agent integration - Works with Claude Code and Codex CLI
## The Problem
Traditional AI interactions treat research as a single-shot query: you ask a question, get an answer, and hope it's accurate. This approach struggles with:
Lack of source transparency - Where did this information come from?
No methodology documentation - How was this answer derived?
Inconsistent quality - Results vary wildly between queries
No bias mitigation - Unexamined assumptions baked into responses
Poor reproducibility - Can't validate or build on previous research
Research Kit solves this by making research a structured, auditable process rather than a black-box interaction.
## Who It's For
Research Kit is designed for anyone who needs rigorous, documented research:
An open source toolkit for conducting structured, rigorous research with AI agents. Move beyond ad-hoc queries to systematic investigation with quality standards and reproducible methodologies.
## Origin & Motivation
Research Kit is a fork of Spec Kit by GitHub, originally built as a personal project to adapt the Specification-Driven Development (SDD) workflow for systematic research.
The deeper motivation behind this project is to demonstrate a simple but powerful idea: AI agents perform significantly better when guided by multiple structured phases and template constraints. Instead of asking an AI to "do research" in a single open-ended prompt, Research Kit breaks the process into 10 distinct phases, each with its own template, quality standards, and output expectations. This structured approach:
Reduces hallucination by constraining AI output to specific, well-defined templates at each phase
Improves consistency by enforcing the same methodology across different research topics
Enables quality control by making each phase reviewable before proceeding to the next
Produces better results by giving the AI clear context boundaries instead of unbounded instructions
If you've ever noticed that AI gives better answers when you break a complex question into smaller parts, Research Kit applies that principle systematically to the entire research workflow.
For details on what changed from the upstream Spec Kit, see The Fork.
## Table of Contents
Origin & Motivation
What is Research Kit?
The Problem
Who It's For
Key Features
Quick Start
Research Workflow
Research Types
Supported AI Agents
Installation
Research CLI Reference
Example Output
Documentation
Prerequisites
Troubleshooting
Contributing
License
## What is Research Kit?
Research Kit is a structured research framework designed for AI agents. It transforms ad-hoc prompting into systematic investigation by providing:
Multi-phase research workflow - From defining research questions to executing comprehensive studies
Quality standards enforcement - Built-in principles for source evaluation, methodology rigor, and bias mitigation
Research type specialization - Tailored approaches for academic, market, technical, and general research
Reproducible methodologies - Documented approaches that can be validated and replicated
Citation management - Integrated BibTeX support for proper source attribution
AI agent integration - Works with Claude Code and Codex CLI
## The Problem
Traditional AI interactions treat research as a single-shot query: you ask a question, get an answer, and hope it's accurate. This approach struggles with:
Lack of source transparency - Where did this information come from?
No methodology documentation - How was this answer derived?
Inconsistent quality - Results vary wildly between queries
No bias mitigation - Unexamined assumptions baked into responses
Poor reproducibility - Can't validate or build on previous research
Research Kit solves this by making research a structured, auditable process rather than a black-box interaction.
## Who It's For
Research Kit is designed for anyone who needs rigorous, documented research:
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/nguyenvanduocit-research-kit/)
- 来源
- awesome · https://github.com/nguyenvanduocit/research-kit
- 按领域浏览
- MCP 服务
- 收录来源
- 10 个独立来源
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。