研究代理启动套件 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
研究代理启动套件 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
研究代理启动套件 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install research-agent-starter-kit
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install research-agent-starter-kit
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/JonasLee12/research-agent-starter-kit
cd research-agent-starter-kit
pip install -e .
# 验证安装
python -c "import research_agent_starter_kit; print('安装成功')"
# 命令行使用
research-agent-starter-kit --help
# 基本用法
research-agent-starter-kit input_file -o output_file
# Python 代码中调用
import research_agent_starter_kit
# 示例
result = research_agent_starter_kit.process("input")
print(result)
# research-agent-starter-kit 配置文件示例(config.yml) app: name: "research-agent-starter-kit" debug: false log_level: "INFO" # 运行时指定配置文件 research-agent-starter-kit --config config.yml # 或通过环境变量配置 export RESEARCH_AGENT_STARTER_KIT_API_KEY="your-key" export RESEARCH_AGENT_STARTER_KIT_OUTPUT_DIR="./output"
Build a local research agent that thinks before writing, checks sources before claiming, and blocks weak formal outputs before delivery.
Use it with Codex, Claude Code, Cursor, or any coding agent that can read local files and follow SKILL.md instructions. The kit itself is file-based and local-first; the agent tool you choose may have its own login, subscription, or API-key requirements.
This starter kit is for dissertations, theses, articles, reports, proposals, and structured research projects where AI assistance must stay evidence-aware, auditable, and honest about its limits.
It does not replace source review, ethics/compliance approval, supervisor judgement, peer review, or institutional credentials. Those limits are visible by design.
cp templates/AGENTS.example.md AGENTS.md
v1.4.0 adds Material Passport and Formal Delivery Guard.
That means formal research artifacts now get a compact evidence passport before they move forward, and final Word/PDF/stakeholder-facing delivery can be blocked when required lock, integrity, citation, compliance, or requirement evidence is missing.
v1.3.1 added release-surface verification and a public sync policy.
That means the starter kit now checks GitHub-visible release surfaces before claiming a public update is complete, and it defines what can be synced from a private project workspace into the public template without leaking private research content.
v1.3.0 added safer Obsidian onboarding and an external-review fallback for users who do not have Claude Code. External review remains advisory only.
Place marking criteria, client requirements, ethics/compliance notes, or formal guidance in university-guidance/, compliance/, or your own project-specific folder. See university-guidance/EXAMPLE_RUBRIC_GUIDE.md for the expected style.
<details> <summary>Customise the starter kit for your project</summary>
If you use Obsidian: Open knowledge-base/ as your Obsidian vault. Do not open the repository root. See Obsidian Setup.
If you do not have Claude Code: use the external-review bundle workflow and paste the generated prompt into a separate Codex, ChatGPT, Claude, Gemini, or human review process. See External Review Options.
```bash git clone https://github.com/JonasLee12/research-agent-starter-kit.git cd research-agent-starter-kit
python3 -m venv .venv source .venv/bin/activate
pip install -r requirements.txt
See research-wiki/ZOTERO_AND_CITATION_WORKFLOW_SPEC.md.
高质量的开源AI工作流套件,值得关注
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
经综合评估,研究代理启动套件 在Agent工作流赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | research-agent-starter-kit |
| 原始描述 | 开源AI工作流:A privacy-first starter kit for research agents: source-first workflows, cogniti。⭐6 · Python |
| Topics | academic-researchai-agentknowledge-base |
| GitHub | https://github.com/JonasLee12/research-agent-starter-kit |
| License | MIT |
| 语言 | Python |
收录时间:2026-06-01 · 更新时间:2026-06-02 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端